WP04 · Draft web edition · as of 2026-10-30
Machine-learning demand forecasting for apparel makers with no sales history
Each weft is one exhibit's own data, normalised; each warp group is a chapter. The probe reads the exhibit's own value where it crosses. Procedural visualisation, not a measurement.
Operate the evidence first
The weft the probe was reading, lifted out of the cloth: the same exhibit at full size, with the probe as its cursor. Choose a weft, step through it, compare its series.
Read-out
Illustrative sequence of evidence stages for a cold-start apparel launch, drawing on hierarchical pooling, preference calibration and controlled pilot design. Node order shows information maturity, not a fixed calendar duration.
Unit: launch evidence stages. Status: illustrative. Sources: S28, S31, S32. Illustrative figures are teaching examples, not measured factory results.
Read this exhibit in its chapter ↗Read-out
Illustrative bounds and midpoints. Prior = 40, 80, 150; post-choice = 50, 85, 140; post-pilot = 55, 105, 180 after an assumed availability and transfer exception; post-repeat = 70, 100, 150 after assumed valid repeat evidence. These are constructed ranges, not statistical intervals, observed demand or guaranteed uncertainty reductions.
Unit: illustrative indexed demand per launch window. Status: illustrative. Sources: S28, S06. Illustrative figures are teaching examples, not measured factory results.
Read this exhibit in its chapter ↗Read-out
Derived GFT control sequence from cited system-value, technical-debt and monitoring guidance. This is a proposed operating design, not an implemented GFT client service or a measured result.
Unit: forecast release and reversion sequence. Status: derived. Sources: S33, S39, S40.
Read this exhibit in its chapter ↗Read-out
Derived GFT operating sequence from cited availability, structured-elicitation, system-value and oversight principles. This is a proposed control design, not evidence of an implemented monthly process or its results.
Unit: forecast-to-outcome sequence. Status: derived. Sources: S06, S29, S33, S36.
Read this exhibit in its chapter ↗The paper's argument
Chapter read-out · hover or focus a thread
Founders and operations leaders of greenfield apparel manufacturers, Demand planners, merchandisers and sales and operations planning teams, Industrial digital teams working with limited data and small technical staffs, Development finance and enterprise advisers assessing apparel launch plans, Researchers studying new-product and new-firm demand forecasting in African markets
0127 min · 4 exhibits
No history is a forecasting condition, not a forecasting ban
A greenfield maker can forecast responsibly when it states what evidence transfers, what remains uncertain and what would change the plan.
01 / 05The thesis
An apparel maker with no sales history should treat forecasting as a disciplined transition from analogue and market priors to calibrated launch evidence, using simple baselines and probabilistic global models only when they beat those priors in cold-start backtests.
14 chapters · 4 parts · 376 minutes
Prepared for: Founders and operations leaders of greenfield apparel manufacturers, Demand planners, merchandisers and sales and operations planning teams, Industrial digital teams working with limited data and small technical staffs, Development finance and enterprise advisers assessing apparel launch plans, Researchers studying new-product and new-firm demand forecasting in African markets
02 / 05Part I · Define the decision and the prior
An apparel maker with no sales history does not face an empty evidence problem. It faces a transfer problem: which analogues, market statistics, expert judgements and early buying signals deserve to shape a launch forecast, and how quickly should their influence decay as real demand arrives? This paper argues that cold-start forecasting should be engineered as an evidence sequence, …
Part I · chapters 01 to 04 · 112 minutes · 21 exhibits
03 / 05Part II · Earn evidence before scale
… not bought as a single model. It begins with a forecast contract that separates latent demand from recorded sales, fixes product and channel grains, and makes stock availability a first-class field. It then builds explicit priors from comparable products, reported trade, population and income indicators, structured expert judgement and calibrated choice research.
Part II · chapters 05 to 07 · 81 minutes · 13 exhibits
04 / 05Part III · Model with scarcity and uncertainty
Small, availability-aware pilots convert those priors into owned evidence. Simple statistical and attribute models remain the benchmarks. Global neural models, Bayesian partial pooling and pretrained time-series models enter only when launch-replay backtests show gains in accuracy, calibration and planning utility. Probabilistic outputs, hierarchical reconciliation and rollback controls connect the model to production decisions without automating commitments.
Part III · chapters 08 to 11 · 104 minutes · 19 exhibits
05 / 05Part IV · Prove value and graduate with evidence
The closing roadmap shows how GFT would move a Cameroon apparel venture from pre-launch priors to a governed forecasting service over eighteen months. The result is not a promise of precise foresight. It is a measurable way to narrow uncertainty while protecting a new maker from false sophistication, stockout-contaminated learning and premature scale.
Part IV · chapters 12 to 14 · 79 minutes · 15 exhibits
The cloth seen from above
Weaving draft · 14 chapters × 68 exhibits
One column per chapter, one knot per exhibit; the glyph is its type family, as on the chips above. Select a knot to open the exhibit below.
Exhibit 01 · chapter 01 · Flow
Read-out
Illustrative sequence of evidence stages for a cold-start apparel launch, drawing on hierarchical pooling, preference calibration and controlled pilot design. Node order shows information maturity, not a fixed calendar duration.
Unit: launch evidence stages. Status: illustrative. Sources: S28, S31, S32. Illustrative figures are teaching examples, not measured factory results.
Read this exhibit in its chapter ↗Read-out
Interlude · findings against chapters
No sales history is not no evidence, but no model can create demand evidence from nothing.S01S08S31
A new firm's cold start is harder than a new SKU's cold start because attribute models still need other products on which to train.S02S05
Recorded sales must be corrected for availability before they can stand in for demand.S06S07
Analogue launch curves and partially pooled priors are more defensible starting points than an unverified complex model.S28S30
Naive forecasts, intermittent-demand methods and equal-weight combinations remain mandatory challengers throughout the model ladder.S09S10S18S20
Global and pretrained models are candidates for borrowing evidence, not proof that a Cameroon apparel launch will transfer from public benchmarks.S21S22S25S26
Usable launch forecasts carry calibrated quantiles and reconcile product, size, channel and market totals.S14S15S16S17
Cold-start validation must replay whole launches with as-of features, not randomise rows across time and products.S02S05S13S37
Calibrated choice research and controlled pilots provide the missing bridge between stated interest and owned purchase history.S31S32
Forecast value depends on governed planning use, drift response and measured decisions, not model loss alone.S33S38S40
Cell strength is the recurrence of each finding's key terms in each chapter's text, computed from this web edition and scaled to the strongest chapter. It is a reading guide, not a citation.
Evidence stays attached
Every knot on the edge is one of the 295 records the chapters cite, sorted by grade. The counters filter them; select a record to read it and to light the chapters that cite it. A grade describes the supplied evidence record, not independent validation by the website; missing references are excluded.
All 295 records shown
c01-S36 · Grade A
Artificial Intelligence Risk Management Framework (AI RMF 1.0)
Human judgment should be employed when deciding on the specific metrics related to AI trustworthiness characteristics and the precise threshold values for those metrics.
2023. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S36 · Grade A
Artificial Intelligence Risk Management Framework (AI RMF 1.0)
Human judgment should be employed when deciding on the specific metrics related to AI trustworthiness characteristics and the precise threshold values for those metrics.
2023. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c03-S44 · Grade A
Population, total
Total population is based on the de facto definition of population, which counts all residents regardless of legal status or citizenship. The values shown are midyear estimates.
2026-10-30. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c03-S45 · Grade A
GNI per capita (constant 2015 US$)
Gross national income is the total income earned by all residents within an economic territory during an accounting period. This indicator is expressed in constant prices, meaning the series has been adjusted to account for price changes over time. The reference year for this adjustment is 2015.
2026-10-30. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c03-S46 · Grade A
Urban population (% of total population)
Urban population refers to people living in urban areas as defined by national statistical offices. Particular caution should be used in interpreting the figures for percentage urban for different countries.
2026-10-30. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S35 · Grade A
The Effects of Weather on Retail Sales
Using monthly data on retail sales and weather data from the National Weather Service, I find that unusual weather has a modest but significant role in explaining monthly sales fluctuations.
2000. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S36 · Grade A
Artificial Intelligence Risk Management Framework (AI RMF 1.0)
Human judgment should be employed when deciding on the specific metrics related to AI trustworthiness characteristics and the precise threshold values for those metrics.
2023. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S41 · Grade A
What are the data sources for UN Comtrade?
The data are sourced directly from countries and submitted to the United Nations Statistics Division.
2026-10-30. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S42 · Grade A
Bilateral asymmetries
Bilateral trade asymmetries occur when the reported exports from country A to country B do not match the reported imports to country B from country A.
2026-10-30. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S43 · Grade A
Trade Map User Guide
Trade Map provides both values and quantities for the trade flows of goods.
2014. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S44 · Grade A
Population, total
Total population is based on the de facto definition of population, which counts all residents regardless of legal status or citizenship.
2026-10-30. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S45 · Grade A
GNI per capita (constant 2015 US$)
Gross national income is the total income earned by all residents within an economic territory during an accounting period.
2026-10-30. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S46 · Grade A
Urban population (% of total population)
Urban population refers to people living in urban areas as defined by national statistical offices.
2026-10-30. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S47 · Grade A
Agricultural production statistics 2010-2024
The agricultural production domain covers data on crop and livestock commodities from production volumes to harvested areas and animal slaughtering rates up to 2024.
2025. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c05-S08 · Grade A
Forecasting: theory and practice
In fact, there may be no historical observations at all for the item of interest, when judgmental methods must be used (e.g., time taken to complete construction of a new airport).
2022. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c05-S14 · Grade A
Strictly Proper Scoring Rules, Prediction, and Estimation
In prediction problems, proper scoring rules encourage the forecaster to make careful assessments and to be honest.
2007. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c05-S16 · Grade A
The M5 uncertainty competition: Results, findings and conclusions
To do so, the competition required the prediction of nine different quantiles (0.005, 0.025, 0.165, 0.250, 0.500, 0.750, 0.835, 0.975, and 0.995), that can sufficiently describe the complete distributions of future sales.
2022. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c05-S20 · Grade A
Forecast combinations: an over 50-year review
That is, equally weighted averages, which ignore past information regarding the precision of individual forecasts and correlations between forecast errors, work reasonably well compared to more sophisticated combination schemes.
2022-09-23. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c05-S30 · Grade A
A New Product Growth for Model Consumer Durables
A growth model for the timing of initial purchase of new products is developed and tested empirically against data for eleven consumer durables.
1969. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c05-S31 · Grade A
Preference Learning and Demand Forecast
This allows us to forecast demand in real purchase settings using inexpensive choice data with small to moderate realization probabilities.
2020. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c05-S32 · Grade A
Controlled experiments on the web: survey and practical guide
Controlled experiments embody the best scientific design for establishing a causal relationship between changes and their influence on user-observable behavior.
2008-07-30. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c05-S36 · Grade A
Artificial Intelligence Risk Management Framework (AI RMF 1.0)
Human judgment should be employed when deciding on the specific metrics related to AI trustworthiness characteristics and the precise threshold values for those metrics.
2023. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c05-S37 · Grade A
Leakage and the reproducibility crisis in machine-learning-based science
Data leakage is a spurious relationship between the independent variables and the target variable that arises as an artifact of the data collection, sampling, or pre-processing strategy.
2023-08-04. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c05-S39 · Grade A
Hidden Technical Debt in Machine Learning Systems
Research solutions that provide a tiny accuracy benefit at the cost of massive increases in system complexity are rarely wise practice.
2015. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c05-S44 · Grade A
Population, total
Total population is based on the de facto definition of population, which counts all residents regardless of legal status or citizenship.
2026-10-30. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c05-S46 · Grade A
Urban population (% of total population)
Urban population refers to people living in urban areas as defined by national statistical offices.
2026-10-30. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c05-S0503 · Grade A
The preregistration revolution
Preregistration distinguishes analyses and outcomes that result from predictions from those that result from postdictions.
2018-03-13. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c06-S36 · Grade A
Artificial Intelligence Risk Management Framework (AI RMF 1.0)
Human judgment should be employed when deciding on the specific metrics related to AI trustworthiness characteristics and the precise threshold values for those metrics.
2023. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c07-S36 · Grade A
Artificial Intelligence Risk Management Framework (AI RMF 1.0)
Human judgment should be employed when deciding on the specific metrics related to AI trustworthiness characteristics and the precise threshold values for those metrics.
2023. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c07-S41 · Grade A
What are the data sources for UN Comtrade?
The data are sourced directly from countries and submitted to the United Nations Statistics Division.
2026-10-30. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c07-S42 · Grade A
Bilateral asymmetries
Bilateral trade asymmetries occur when the reported exports from country A to country B do not match the reported imports to country B from country A.
2026-10-30. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S36 · Grade A
Artificial Intelligence Risk Management Framework (AI RMF 1.0)
Human judgment should be employed when deciding on the specific metrics related to AI trustworthiness characteristics and the precise threshold values for those metrics.
2023. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c12-S36 · Grade A
Artificial Intelligence Risk Management Framework (AI RMF 1.0)
Human judgment should be employed when deciding on the specific metrics related to AI trustworthiness characteristics and the precise threshold values for those metrics.
2023. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c13-S36 · Grade A
Artificial Intelligence Risk Management Framework (AI RMF 1.0)
Human judgment should be employed when deciding on the specific metrics related to AI trustworthiness characteristics and the precise threshold values for those metrics.
2023. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c14-S33 · Grade A
Rules of Machine Learning: Best Practices for ML Engineering
When this starts happening more often, it is time to revisit the objective of your model.
2025-08-25. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c14-S36 · Grade A
Artificial Intelligence Risk Management Framework (AI RMF 1.0)
Human judgment should be employed when deciding on the specific metrics related to AI trustworthiness characteristics and the precise threshold values for those metrics.
2023. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c14-S40 · Grade A
MLOps: Continuous delivery and automation pipelines in machine learning
Monitoring lets you detect performance degradation and model staleness.
2024-08-28. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S01 · Grade B
Demand Forecasting in the Fashion Industry: A Review
This is especially the case in the fashion industry, where demand uncertainty, lack of historical data and seasonal trends usually coexist.
2013. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S02 · Grade B
Fashion Retail: Forecasting Demand for New Items
To address this problem, we present a study of large scale fashion sales data and directly infer which clothing/footwear attributes and merchandising factors drove demand for those items.
2019-06-27. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S03 · Grade B
Product age based demand forecast model for fashion retail
We have modeled sales of a fashion item in a store as a function of its age, attributes, selling price, temporal and store features.
2020-07-10. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S04 · Grade B
Demand Forecasting for Multichannel Fashion Retailers by Integrating Clustering and Machine Learning Algorithms
Therefore, it is recommended that future researchers consider other external predictor variables such as holidays (school and business), commercially relevant events (Easter, Christmas), extraordinary events (e.g., a pandemic), and economic conditions when predicting demand for a more specific region or different sales channels.
2021-09-03. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S05 · Grade B
Deep learning for new fashion product demand prediction: integrating visual similarity and demand correction in cold-start scenarios
By matching new products to these clusters, the model transfers corrected demand signals from similar historical products to estimate future demand.
2026-01-08. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S06 · Grade B
Retail forecasting: research and practice
Demand estimates using only sales data would result in a negative bias in demand estimates of the focal product.
2018-11-19. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S07 · Grade B
FreshRetailNet-LT: A Stockout-Annotated Censored Demand Dataset for Latent Demand Recovery and Forecasting in Fresh Retail
Consequently, the sales-equals-demand assumption collapses in the event of product stockouts, as observed sales volumes systematically under-represent the latent demand.
2026. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S08 · Grade B
Forecasting: theory and practice
In fact, there may be no historical observations at all for the item of interest, when judgmental methods must be used (e.g., time taken to complete construction of a new airport).
2022. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S09 · Grade B
Statistical and Machine Learning forecasting methods: Concerns and ways forward
Even Naive 2 (a seasonal Random Walk (RW) benchmark) is more accurate than half of the ML methods.
2018-03-27. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S10 · Grade B
The M4 Competition: Results, findings, conclusion and way forward
The six pure ML methods performed poorly, with none of them being more accurate than the combination benchmark and only one being more accurate than Naïve2.
2018. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S11 · Grade B
M5 accuracy competition: Results, findings, and conclusions
The main objective in the M5 “Accuracy” competition was to accurately predict 42,840 time series representing the hierarchical unit sales for the largest retail company in the world by revenue, Walmart.
2022. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S12 · Grade B
Another look at measures of forecast accuracy
Instead, we propose that the mean absolute scaled error become the standard measure for comparing forecast accuracy across multiple time series.
2006. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S13 · Grade B
3.1. Cross-validation: evaluating estimator performance
Note that unlike standard cross-validation methods, successive training sets are supersets of those that come before them.
2026-10-30. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S14 · Grade B
Strictly Proper Scoring Rules, Prediction, and Estimation
In prediction problems, proper scoring rules encourage the forecaster to make careful assessments and to be honest.
2007. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S15 · Grade B
Accurate Uncertainties for Deep Learning Using Calibrated Regression
Here, we propose a simple procedure for calibrating any regression algorithm; when applied to Bayesian and probabilistic models, it is guaranteed to produce calibrated uncertainty estimates given enough data.
2018-07-03. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S16 · Grade B
The M5 uncertainty competition: Results, findings and conclusions
To do so, the competition required the prediction of nine different quantiles (0.005, 0.025, 0.165, 0.250, 0.500, 0.750, 0.835, 0.975, and 0.995), that can sufficiently describe the complete distributions of future sales.
2022. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S17 · Grade B
Optimal Forecast Reconciliation for Hierarchical and Grouped Time Series Through Trace Minimization
Our approach minimizes the mean squared error of the coherent forecasts across the entire collection of time series under the assumption of unbiasedness.
2019. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S18 · Grade B
The accuracy of intermittent demand estimates
Intermittent demand appears sporadically, with some time periods showing no demand at all.
2005. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S20 · Grade B
Forecast combinations: an over 50-year review
That is, equally weighted averages, which ignore past information regarding the precision of individual forecasts and correlations between forecast errors, work reasonably well compared to more sophisticated combination schemes.
2022-09-23. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S21 · Grade B
DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks
In this paper we propose DeepAR, a methodology for producing accurate probabilistic forecasts, based on training an auto regressive recurrent network model on a large number of related time series.
2019-02-22. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S22 · Grade B
Principles and Algorithms for Forecasting Groups of Time Series: Locality and Globality
The global approach fits a single function to all series.
2021-03-26. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S25 · Grade B
Chronos: Learning the Language of Time Series
Chronos tokenizes time series values using scaling and quantization into a fixed vocabulary and trains existing transformer-based language model architectures on these tokenized time series via the cross-entropy loss.
2024-11-04. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S26 · Grade B
A decoder-only foundation model for time-series forecasting
Motivated by recent advances in large language models for Natural Language Processing (NLP), we design a time-series foundation model for forecasting whose out-of-the-box zero-shot performance on a variety of public datasets comes close to the accuracy of state-of-the-art supervised forecasting models for each individual dataset.
2024-04-17. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S28 · Grade B
A hierarchical Bayesian regression model that reduces uncertainty in material demand predictions
Bayesian regression models permit the use of smaller datasets through hierarchical modeling (Vehtari et al., 2017) which allows sharing of information across heterogeneous sites.
2022-10-17. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S29 · Grade B
Delphi Method
Today, groups of experts or stakeholders use online tools such as ExpertLens to anonymously answer questionnaires, receive feedback that represents the “group response,” discuss, and revise their answers to see whether they can approach expert consensus.
2023-12-29. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S30 · Grade B
A New Product Growth for Model Consumer Durables
A growth model for the timing of initial purchase of new products is developed and tested empirically against data for eleven consumer durables.
1969. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S31 · Grade B
Preference Learning and Demand Forecast
This allows us to forecast demand in real purchase settings using inexpensive choice data with small to moderate realization probabilities.
2020. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S32 · Grade B
Controlled experiments on the web: survey and practical guide
Controlled experiments embody the best scientific design for establishing a causal relationship between changes and their influence on user-observable behavior.
2008-07-30. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S37 · Grade B
Leakage and the reproducibility crisis in machine-learning-based science
Data leakage is a spurious relationship between the independent variables and the target variable that arises as an artifact of the data collection, sampling, or pre-processing strategy.
2023-08-04. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S38 · Grade B
A Survey on Concept Drift Adaptation
Assuming a general knowledge of supervised learning in this paper we characterize adaptive learning process, categorize existing strategies for handling concept drift, discuss the most representative, distinct and popular techniques and algorithms, discuss evaluation methodology of adaptive algorithms, and present a set of illustrative applications.
2014-04-30. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S39 · Grade B
Hidden Technical Debt in Machine Learning Systems
Research solutions that provide a tiny accuracy benefit at the cost of massive increases in system complexity are rarely wise practice.
2015. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S0101 · Grade B
On the use of learning-based forecasting methods for ameliorating fashion business processes: A position paper
A plethora of business processes are involved in this large-scale industry, but due to the generally short life-cycle of clothing items, supply-chain management and retailing strategies are crucial for good market performance.
2022-11-09. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S0102 · Grade B
Forecasting: Principles and Practice (3rd ed), Chapter 6: Judgmental forecasts
In many cases, judgmental forecasting is the only option, such as when there is a complete lack of historical data, or when a new product is being launched, or when a new competitor enters the market, or during completely new and unique market conditions.
2021-05-31. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S01 · Grade B
Demand Forecasting in the Fashion Industry: A Review
This is especially the case in the fashion industry, where demand uncertainty, lack of historical data and seasonal trends usually coexist.
2013. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S02 · Grade B
Fashion Retail: Forecasting Demand for New Items
To address this problem, we present a study of large scale fashion sales data and directly infer which clothing/footwear attributes and merchandising factors drove demand for those items.
2019-06-27. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S03 · Grade B
Product age based demand forecast model for fashion retail
We have modeled sales of a fashion item in a store as a function of its age, attributes, selling price, temporal and store features.
2020-07-10. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S04 · Grade B
Demand Forecasting for Multichannel Fashion Retailers by Integrating Clustering and Machine Learning Algorithms
Therefore, it is recommended that future researchers consider other external predictor variables such as holidays (school and business), commercially relevant events (Easter, Christmas), extraordinary events (e.g., a pandemic), and economic conditions when predicting demand for a more specific region or different sales channels.
2021-09-03. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S05 · Grade B
Deep learning for new fashion product demand prediction: integrating visual similarity and demand correction in cold-start scenarios
By matching new products to these clusters, the model transfers corrected demand signals from similar historical products to estimate future demand.
2026-01-08. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S06 · Grade B
Retail forecasting: research and practice
Demand estimates using only sales data would result in a negative bias in demand estimates of the focal product.
2018-11-19. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S07 · Grade B
FreshRetailNet-LT: A Stockout-Annotated Censored Demand Dataset for Latent Demand Recovery and Forecasting in Fresh Retail
Consequently, the sales-equals-demand assumption collapses in the event of product stockouts, as observed sales volumes systematically under-represent the latent demand.
2026. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S08 · Grade B
Forecasting: theory and practice
In fact, there may be no historical observations at all for the item of interest, when judgmental methods must be used (e.g., time taken to complete construction of a new airport).
2022. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S11 · Grade B
M5 accuracy competition: Results, findings, and conclusions
The main objective in the M5 “Accuracy” competition was to accurately predict 42,840 time series representing the hierarchical unit sales for the largest retail company in the world by revenue, Walmart.
2022. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S12 · Grade B
Another look at measures of forecast accuracy
Instead, we propose that the mean absolute scaled error become the standard measure for comparing forecast accuracy across multiple time series.
2006. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S13 · Grade B
3.1. Cross-validation: evaluating estimator performance
Note that unlike standard cross-validation methods, successive training sets are supersets of those that come before them.
2026-10-30. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S14 · Grade B
Strictly Proper Scoring Rules, Prediction, and Estimation
In prediction problems, proper scoring rules encourage the forecaster to make careful assessments and to be honest.
2007. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S15 · Grade B
Accurate Uncertainties for Deep Learning Using Calibrated Regression
Here, we propose a simple procedure for calibrating any regression algorithm; when applied to Bayesian and probabilistic models, it is guaranteed to produce calibrated uncertainty estimates given enough data.
2018-07-03. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S16 · Grade B
The M5 uncertainty competition: Results, findings and conclusions
To do so, the competition required the prediction of nine different quantiles (0.005, 0.025, 0.165, 0.250, 0.500, 0.750, 0.835, 0.975, and 0.995), that can sufficiently describe the complete distributions of future sales.
2022. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S17 · Grade B
Optimal Forecast Reconciliation for Hierarchical and Grouped Time Series Through Trace Minimization
Our approach minimizes the mean squared error of the coherent forecasts across the entire collection of time series under the assumption of unbiasedness.
2019. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S18 · Grade B
The accuracy of intermittent demand estimates
Intermittent demand appears sporadically, with some time periods showing no demand at all.
2005. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S19 · Grade B
On the bias of intermittent demand estimates
In addition, a modification to his method that gives approximately unbiased demand per period estimates is introduced.
2001. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S22 · Grade B
Principles and Algorithms for Forecasting Groups of Time Series: Locality and Globality
The global approach fits a single function to all series.
2021-03-26. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S24 · Grade B
Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting
The TFT also uses specialized components for the judicious selection of relevant features and a series of gating layers to suppress unnecessary components, enabling high performance in a wide range of regimes.
2020-09-27. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S28 · Grade B
A hierarchical Bayesian regression model that reduces uncertainty in material demand predictions
Bayesian regression models permit the use of smaller datasets through hierarchical modeling (Vehtari et al., 2017) which allows sharing of information across heterogeneous sites.
2022-10-17. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S37 · Grade B
Leakage and the reproducibility crisis in machine-learning-based science
Data leakage is a spurious relationship between the independent variables and the target variable that arises as an artifact of the data collection, sampling, or pre-processing strategy.
2023-08-04. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S39 · Grade B
Hidden Technical Debt in Machine Learning Systems
Research solutions that provide a tiny accuracy benefit at the cost of massive increases in system complexity are rarely wise practice.
2015. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S0201 · Grade B
Information Distortion in a Supply Chain: The Bullwhip Effect
This paper claims that the information transferred in the form of "orders" tends to be distorted and can misguide upstream members in their inventory and production decisions.
1997-04. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S0202 · Grade B
Forecasting: Principles and Practice (3rd ed), Chapter 1: Getting started
In the early stages of a forecasting project, decisions need to be made about what should be forecast.
2021-05-31. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S0203 · Grade B
Forecasting: Principles and Practice (3rd ed), Chapter 13: Some practical forecasting issues
With Croston’s method, we construct two new series from our original time series by noting which time periods contain zero values, and which periods contain non-zero values.
2021-05-31. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c03-S01 · Grade B
Demand Forecasting in the Fashion Industry: A Review
This is especially the case in the fashion industry, where demand uncertainty, lack of historical data and seasonal trends usually coexist.
2013. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c03-S02 · Grade B
Fashion Retail: Forecasting Demand for New Items
To address this problem, we present a study of large scale fashion sales data and directly infer which clothing/footwear attributes and merchandising factors drove demand for those items.
2019-06-27. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c03-S03 · Grade B
Product age based demand forecast model for fashion retail
We have modeled sales of a fashion item in a store as a function of its age, attributes, selling price, temporal and store features.
2020-07-10. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c03-S04 · Grade B
Demand Forecasting for Multichannel Fashion Retailers by Integrating Clustering and Machine Learning Algorithms
Therefore, it is recommended that future researchers consider other external predictor variables such as holidays (school and business), commercially relevant events (Easter, Christmas), extraordinary events (e.g., a pandemic), and economic conditions when predicting demand for a more specific region or different sales channels.
2021-09-03. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c03-S05 · Grade B
Deep learning for new fashion product demand prediction: integrating visual similarity and demand correction in cold-start scenarios
By matching new products to these clusters, the model transfers corrected demand signals from similar historical products to estimate future demand.
2026-01-08. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c03-S08 · Grade B
Forecasting: theory and practice
In fact, there may be no historical observations at all for the item of interest, when judgmental methods must be used (e.g., time taken to complete construction of a new airport).
2022. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c03-S14 · Grade B
Strictly Proper Scoring Rules, Prediction, and Estimation
In prediction problems, proper scoring rules encourage the forecaster to make careful assessments and to be honest.
2007-03. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c03-S22 · Grade B
Principles and Algorithms for Forecasting Groups of Time Series: Locality and Globality
The global approach fits a single function to all series.
2021-03-26. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c03-S28 · Grade B
A hierarchical Bayesian regression model that reduces uncertainty in material demand predictions
In this paper, we propose a Bayesian hierarchical model that can simultaneously identify heterogeneous demand parameters (like price and income elasticities) for individual regions and sectors, as well as global parameters.
2023-02. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c03-S30 · Grade B
A New Product Growth for Model Consumer Durables
A growth model for the timing of initial purchase of new products is developed and tested empirically against data for eleven consumer durables.
1969. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S01 · Grade B
Demand Forecasting in the Fashion Industry: A Review
This is especially the case in the fashion industry, where demand uncertainty, lack of historical data and seasonal trends usually coexist.
2013. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S02 · Grade B
Fashion Retail: Forecasting Demand for New Items
To address this problem, we present a study of large scale fashion sales data and directly infer which clothing/footwear attributes and merchandising factors drove demand for those items.
2019-06-27. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S03 · Grade B
Product age based demand forecast model for fashion retail
We have modeled sales of a fashion item in a store as a function of its age, attributes, selling price, temporal and store features.
2020-07-10. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S04 · Grade B
Demand Forecasting for Multichannel Fashion Retailers by Integrating Clustering and Machine Learning Algorithms
Therefore, it is recommended that future researchers consider other external predictor variables such as holidays (school and business), commercially relevant events (Easter, Christmas), extraordinary events (e.g., a pandemic), and economic conditions when predicting demand for a more specific region or different sales channels.
2021-09-03. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S06 · Grade B
Retail forecasting: research and practice
Demand estimates using only sales data would result in a negative bias in demand estimates of the focal product.
2018-11-19. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S08 · Grade B
Forecasting: theory and practice
In fact, there may be no historical observations at all for the item of interest, when judgmental methods must be used (e.g., time taken to complete construction of a new airport).
2022. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S09 · Grade B
Statistical and Machine Learning forecasting methods: Concerns and ways forward
Even Naive 2 (a seasonal Random Walk (RW) benchmark) is more accurate than half of the ML methods.
2018-03-27. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S10 · Grade B
The M4 Competition: Results, findings, conclusion and way forward
The six pure ML methods performed poorly, with none of them being more accurate than the combination benchmark and only one being more accurate than Naïve2.
2018. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S12 · Grade B
Another look at measures of forecast accuracy
Instead, we propose that the mean absolute scaled error become the standard measure for comparing forecast accuracy across multiple time series.
2006. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S13 · Grade B
3.1. Cross-validation: evaluating estimator performance
Note that unlike standard cross-validation methods, successive training sets are supersets of those that come before them.
2026-10-30. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S24 · Grade B
Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting
The TFT also uses specialized components for the judicious selection of relevant features and a series of gating layers to suppress unnecessary components, enabling high performance in a wide range of regimes.
2020-09-27. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S28 · Grade B
A hierarchical Bayesian regression model that reduces uncertainty in material demand predictions
Bayesian regression models permit the use of smaller datasets through hierarchical modeling (Vehtari et al., 2017) which allows sharing of information across heterogeneous sites.
2022-10-17. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S34 · Grade B
Predicting consumer behavior with Web search
We conclude that in the absence of other data sources, or where small improvements in predictive performance are material, search queries provide a useful guide to the near future.
2010. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S37 · Grade B
Leakage and the reproducibility crisis in machine-learning-based science
Data leakage is a spurious relationship between the independent variables and the target variable that arises as an artifact of the data collection, sampling, or pre-processing strategy.
2023-08-04. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S38 · Grade B
A Survey on Concept Drift Adaptation
Assuming a general knowledge of supervised learning in this paper we characterize adaptive learning process, categorize existing strategies for handling concept drift, discuss the most representative, distinct and popular techniques and algorithms, discuss evaluation methodology of adaptive algorithms, and present a set of illustrative applications.
2014-04-30. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S39 · Grade B
Hidden Technical Debt in Machine Learning Systems
Research solutions that provide a tiny accuracy benefit at the cost of massive increases in system complexity are rarely wise practice.
2015. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S0401 · Grade B
Forecasting: Principles and Practice (3rd ed), Section 7.6: Forecasting with regression
Ex-ante forecasts are those that are made using only the information that is available in advance. Therefore in order to generate ex-ante forecasts, the model requires forecasts of the predictors.
2021-05-31. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S0402 · Grade B
On the use of learning-based forecasting methods for ameliorating fashion business processes: A position paper
A plethora of business processes are involved in this large-scale industry, but due to the generally short life-cycle of clothing items, supply-chain management and retailing strategies are crucial for good market performance.
2022-11-09. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S0403 · Grade B
Forecasting: Principles and Practice (3rd ed), Chapter 10: Dynamic regression models
For example, the effects of holidays, competitor activity, changes in the law, the wider economy, or other external variables, may explain some of the historical variation and may lead to more accurate forecasts.
2021-05-31. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c05-S01 · Grade B
Demand Forecasting in the Fashion Industry: A Review
This is especially the case in the fashion industry, where demand uncertainty, lack of historical data and seasonal trends usually coexist.
2013. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c05-S02 · Grade B
Fashion Retail: Forecasting Demand for New Items
To address this problem, we present a study of large scale fashion sales data and directly infer which clothing/footwear attributes and merchandising factors drove demand for those items.
2019-06-27. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c05-S03 · Grade B
Product age based demand forecast model for fashion retail
We have modeled sales of a fashion item in a store as a function of its age, attributes, selling price, temporal and store features.
2020-07-10. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c05-S06 · Grade B
Retail forecasting: research and practice
Demand estimates using only sales data would result in a negative bias in demand estimates of the focal product.
2018-11-19. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c05-S07 · Grade B
FreshRetailNet-LT: A Stockout-Annotated Censored Demand Dataset for Latent Demand Recovery and Forecasting in Fresh Retail
Consequently, the sales-equals-demand assumption collapses in the event of product stockouts, as observed sales volumes systematically under-represent the latent demand.
2026. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c05-S28 · Grade B
A hierarchical Bayesian regression model that reduces uncertainty in material demand predictions
Bayesian regression models permit the use of smaller datasets through hierarchical modeling (Vehtari et al., 2017) which allows sharing of information across heterogeneous sites.
2022-10-17. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c05-S29 · Grade B
Delphi Method
Today, groups of experts or stakeholders use online tools such as ExpertLens to anonymously answer questionnaires, receive feedback that represents the "group response," discuss, and revise their answers to see whether they can approach expert consensus.
2023-12-29. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c05-S33 · Grade B
Rules of Machine Learning: Best Practices for ML Engineering
If there is some change that improves log loss but degrades the performance of the system, look for another feature.
2025-08-25. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c05-S40 · Grade B
MLOps: Continuous delivery and automation pipelines in machine learning
Therefore, you need to track summary statistics of your data and monitor the online performance of your model to send notifications or roll back when values deviate from your expectations.
2024-08-28. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c05-S48 · Grade B
Forecasting future demand for large-screen television sets using conjoint analysis with diffusion model
First, to investigate consumer preferences for product attributes, we use conjoint analysis to estimate the utility function of consumers.
2006. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c05-S0501 · Grade B
Forecasting: Principles and Practice (3rd ed.), Chapter 6: Judgmental forecasts
Customers do not always do what they say they will. Many studies have found a positive correlation between purchase intentions and purchase behaviour; however, the strength of these correlations varies substantially.
2026-10-30. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c05-S0502 · Grade B
Hypothetical Bias
Hypothetical bias occurs when individuals report unrealistic behaviours or values to researchers in surveys or in experimental studies. In other words, what individuals say they would do hypothetically is not necessarily what they would do in reality.
2020. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c06-S04 · Grade B
Demand Forecasting for Multichannel Fashion Retailers by Integrating Clustering and Machine Learning Algorithms
Therefore, it is recommended that future researchers consider other external predictor variables such as holidays (school and business), commercially relevant events (Easter, Christmas), extraordinary events (e.g., a pandemic), and economic conditions when predicting demand for a more specific region or different sales channels.
2021-09-03. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c06-S06 · Grade B
Retail forecasting: research and practice
Demand estimates using only sales data would result in a negative bias in demand estimates of the focal product.
2018-11-19. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c06-S07 · Grade B
FreshRetailNet-LT: A Stockout-Annotated Censored Demand Dataset for Latent Demand Recovery and Forecasting in Fresh Retail
Consequently, the sales-equals-demand assumption collapses in the event of product stockouts, as observed sales volumes systematically under-represent the latent demand.
2026. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c06-S11 · Grade B
M5 accuracy competition: Results, findings, and conclusions
The main objective in the M5 “Accuracy” competition was to accurately predict 42,840 time series representing the hierarchical unit sales for the largest retail company in the world by revenue, Walmart.
2022. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c06-S28 · Grade B
A hierarchical Bayesian regression model that reduces uncertainty in material demand predictions
Bayesian regression models permit the use of smaller datasets through hierarchical modeling (Vehtari et al., 2017) which allows sharing of information across heterogeneous sites.
2022-10-17. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c06-S32 · Grade B
Controlled experiments on the web: survey and practical guide
Controlled experiments embody the best scientific design for establishing a causal relationship between changes and their influence on user-observable behavior.
2008-07-30. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c07-S02 · Grade B
Fashion Retail: Forecasting Demand for New Items
To address this problem, we present a study of large scale fashion sales data and directly infer which clothing/footwear attributes and merchandising factors drove demand for those items.
2019-06-27. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c07-S03 · Grade B
Product age based demand forecast model for fashion retail
We have modeled sales of a fashion item in a store as a function of its age, attributes, selling price, temporal and store features.
2020-07-10. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c07-S04 · Grade B
Demand Forecasting for Multichannel Fashion Retailers by Integrating Clustering and Machine Learning Algorithms
Therefore, it is recommended that future researchers consider other external predictor variables such as holidays (school and business), commercially relevant events (Easter, Christmas), extraordinary events (e.g., a pandemic), and economic conditions when predicting demand for a more specific region or different sales channels.
2021-09-03. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c07-S05 · Grade B
Deep learning for new fashion product demand prediction: integrating visual similarity and demand correction in cold-start scenarios
By matching new products to these clusters, the model transfers corrected demand signals from similar historical products to estimate future demand.
2026-01-08. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c07-S06 · Grade B
Retail forecasting: research and practice
Demand estimates using only sales data would result in a negative bias in demand estimates of the focal product.
2018-11-19. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c07-S07 · Grade B
FreshRetailNet-LT: A Stockout-Annotated Censored Demand Dataset for Latent Demand Recovery and Forecasting in Fresh Retail
Consequently, the sales-equals-demand assumption collapses in the event of product stockouts, as observed sales volumes systematically under-represent the latent demand.
2026. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c07-S18 · Grade B
The accuracy of intermittent demand estimates
Intermittent demand appears sporadically, with some time periods showing no demand at all.
2005. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c07-S19 · Grade B
On the bias of intermittent demand estimates
In addition, a modification to his method that gives approximately unbiased demand per period estimates is introduced.
2001. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c07-S34 · Grade B
Predicting consumer behavior with Web search
We conclude that in the absence of other data sources, or where small improvements in predictive performance are material, search queries provide a useful guide to the near future.
2010. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c07-S35 · Grade B
The Effects of Weather on Retail Sales
Using monthly data on retail sales and weather data from the National Weather Service, I find that unusual weather has a modest but significant role in explaining monthly sales fluctuations.
2000. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c07-S37 · Grade B
Leakage and the reproducibility crisis in machine-learning-based science
Data leakage is a spurious relationship between the independent variables and the target variable that arises as an artifact of the data collection, sampling, or pre-processing strategy.
2023-08-04. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c07-S39 · Grade B
Hidden Technical Debt in Machine Learning Systems
Research solutions that provide a tiny accuracy benefit at the cost of massive increases in system complexity are rarely wise practice.
2015. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c07-S0701 · Grade B
Datasheets for Datasets
By analogy, we propose that every dataset be accompanied with a datasheet that documents its motivation, composition, collection process, recommended uses, and so on.
2021-12-01. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c07-S0702 · Grade B
Infrastructure for Usable Machine Learning: The Stanford DAWN Project
This expense comes not from a need for new and improved statistical models but instead from a lack of systems and tools for supporting end-to-end machine learning application development, from data preparation and labeling to productionization and monitoring.
2017-05-22. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c08-S02 · Grade B
Fashion Retail: Forecasting Demand for New Items
To address this problem, we present a study of large scale fashion sales data and directly infer which clothing/footwear attributes and merchandising factors drove demand for those items.
2019-06-27. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c08-S03 · Grade B
Product age based demand forecast model for fashion retail
We have modeled sales of a fashion item in a store as a function of its age, attributes, selling price, temporal and store features.
2020-07-10. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c08-S08 · Grade B
Forecasting: theory and practice
In fact, there may be no historical observations at all for the item of interest, when judgmental methods must be used (e.g., time taken to complete construction of a new airport).
2022. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c08-S09 · Grade B
Statistical and Machine Learning forecasting methods: Concerns and ways forward
Even Naive 2 (a seasonal Random Walk (RW) benchmark) is more accurate than half of the ML methods.
2018-03-27. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c08-S10 · Grade B
The M4 Competition: Results, findings, conclusion and way forward
The six pure ML methods performed poorly, with none of them being more accurate than the combination benchmark and only one being more accurate than Naïve2.
2018. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c08-S12 · Grade B
Another look at measures of forecast accuracy
Instead, we propose that the mean absolute scaled error become the standard measure for comparing forecast accuracy across multiple time series.
2006. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c08-S18 · Grade B
The accuracy of intermittent demand estimates
Intermittent demand appears sporadically, with some time periods showing no demand at all.
2005. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c08-S19 · Grade B
On the bias of intermittent demand estimates
In addition, a modification to his method that gives approximately unbiased demand per period estimates is introduced.
2001. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c08-S20 · Grade B
Forecast combinations: an over 50-year review
That is, equally weighted averages, which ignore past information regarding the precision of individual forecasts and correlations between forecast errors, work reasonably well compared to more sophisticated combination schemes.
2022-09-23. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c08-S30 · Grade B
A New Product Growth for Model Consumer Durables
A growth model for the timing of initial purchase of new products is developed and tested empirically against data for eleven consumer durables.
1969. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c08-S39 · Grade B
Hidden Technical Debt in Machine Learning Systems
Research solutions that provide a tiny accuracy benefit at the cost of massive increases in system complexity are rarely wise practice.
2015. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c09-S02 · Grade B
Fashion Retail: Forecasting Demand for New Items
To address this problem, we present a study of large scale fashion sales data and directly infer which clothing/footwear attributes and merchandising factors drove demand for those items.
2019-06-27. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c09-S05 · Grade B
Deep learning for new fashion product demand prediction: integrating visual similarity and demand correction in cold-start scenarios
By matching new products to these clusters, the model transfers corrected demand signals from similar historical products to estimate future demand.
2026-01-08. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c09-S21 · Grade B
DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks
In this paper we propose DeepAR, a methodology for producing accurate probabilistic forecasts, based on training an auto regressive recurrent network model on a large number of related time series.
2019-02-22. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c09-S22 · Grade B
Principles and Algorithms for Forecasting Groups of Time Series: Locality and Globality
The global approach fits a single function to all series.
2021-03-26. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c09-S23 · Grade B
N-BEATS: Neural basis expansion analysis for interpretable time series forecasting
The architecture has a number of desirable properties, being interpretable, applicable without modification to a wide array of target domains, and fast to train.
2020-02-20. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c09-S24 · Grade B
Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting
The TFT also uses specialized components for the judicious selection of relevant features and a series of gating layers to suppress unnecessary components, enabling high performance in a wide range of regimes.
2020-09-27. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c09-S28 · Grade B
A hierarchical Bayesian regression model that reduces uncertainty in material demand predictions
Bayesian regression models permit the use of smaller datasets through hierarchical modeling (Vehtari et al., 2017) which allows sharing of information across heterogeneous sites.
2022-10-17. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c09-S37 · Grade B
Leakage and the reproducibility crisis in machine-learning-based science
Data leakage is a spurious relationship between the independent variables and the target variable that arises as an artifact of the data collection, sampling, or pre-processing strategy.
2023-08-04. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c09-S38 · Grade B
A Survey on Concept Drift Adaptation
Assuming a general knowledge of supervised learning in this paper we characterize adaptive learning process, categorize existing strategies for handling concept drift, discuss the most representative, distinct and popular techniques and algorithms, discuss evaluation methodology of adaptive algorithms, and present a set of illustrative applications.
2014-04-30. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c09-S39 · Grade B
Hidden Technical Debt in Machine Learning Systems
Research solutions that provide a tiny accuracy benefit at the cost of massive increases in system complexity are rarely wise practice.
2015. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c10-S01 · Grade B
Demand Forecasting in the Fashion Industry: A Review
This is especially the case in the fashion industry, where demand uncertainty, lack of historical data and seasonal trends usually coexist.
2013. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c10-S12 · Grade B
Another look at measures of forecast accuracy
Instead, we propose that the mean absolute scaled error become the standard measure for comparing forecast accuracy across multiple time series.
2006. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c10-S14 · Grade B
Strictly Proper Scoring Rules, Prediction, and Estimation
In prediction problems, proper scoring rules encourage the forecaster to make careful assessments and to be honest.
2007-03. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c10-S25 · Grade B
Chronos: Learning the Language of Time Series
Chronos tokenizes time series values using scaling and quantization into a fixed vocabulary and trains existing transformer-based language model architectures on these tokenized time series via the cross-entropy loss.
2024-11-04. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c10-S26 · Grade B
A decoder-only foundation model for time-series forecasting
Our model is based on pretraining a patched-decoder style attention model on a large time-series corpus, and can work well across different forecasting history lengths, prediction lengths and temporal granularities.
2024-04-17. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c10-S27 · Grade B
Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting
We present Lag-Llama, a general-purpose foundation model for univariate probabilistic time series forecasting based on a decoder-only transformer architecture that uses lags as covariates.
2024-02-08. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c10-S37 · Grade B
Leakage and the reproducibility crisis in machine-learning-based science
Data leakage is a spurious relationship between the independent variables and the target variable that arises as an artifact of the data collection, sampling, or pre-processing strategy.
2023-08-04. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c10-S38 · Grade B
A Survey on Concept Drift Adaptation
Concept drift primarily refers to an online supervised learning scenario when the relation between the in- put data and the target variable changes over time.
2014-04-30. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c10-S39 · Grade B
Hidden Technical Debt in Machine Learning Systems
Research solutions that provide a tiny accuracy benefit at the cost of massive increases in system complexity are rarely wise practice.
2015. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S01 · Grade B
Demand Forecasting in the Fashion Industry: A Review
This is especially the case in the fashion industry, where demand uncertainty, lack of historical data and seasonal trends usually coexist.
2013. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S02 · Grade B
Fashion Retail: Forecasting Demand for New Items
To address this problem, we present a study of large scale fashion sales data and directly infer which clothing/footwear attributes and merchandising factors drove demand for those items.
2019-06-27. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S03 · Grade B
Product age based demand forecast model for fashion retail
We have modeled sales of a fashion item in a store as a function of its age, attributes, selling price, temporal and store features.
2020-07-10. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S04 · Grade B
Demand Forecasting for Multichannel Fashion Retailers by Integrating Clustering and Machine Learning Algorithms
Therefore, it is recommended that future researchers consider other external predictor variables such as holidays (school and business), commercially relevant events (Easter, Christmas), extraordinary events (e.g., a pandemic), and economic conditions when predicting demand for a more specific region or different sales channels.
2021-09-03. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S06 · Grade B
Retail forecasting: research and practice
Demand estimates using only sales data would result in a negative bias in demand estimates of the focal product.
2018-11-19. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S07 · Grade B
FreshRetailNet-LT: A Stockout-Annotated Censored Demand Dataset for Latent Demand Recovery and Forecasting in Fresh Retail
Consequently, the sales-equals-demand assumption collapses in the event of product stockouts, as observed sales volumes systematically under-represent the latent demand.
2026. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S08 · Grade B
Forecasting: theory and practice
In fact, there may be no historical observations at all for the item of interest, when judgmental methods must be used (e.g., time taken to complete construction of a new airport).
2022. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S11 · Grade B
M5 accuracy competition: Results, findings, and conclusions
The main objective in the M5 Accuracy competition was to accurately predict 42,840 time series representing the hierarchical unit sales for the largest retail company in the world by revenue, Walmart.
2022. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S12 · Grade B
Another look at measures of forecast accuracy
Instead, we propose that the mean absolute scaled error become the standard measure for comparing forecast accuracy across multiple time series.
2006. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S14 · Grade B
Strictly Proper Scoring Rules, Prediction, and Estimation
In prediction problems, proper scoring rules encourage the forecaster to make careful assessments and to be honest.
2007. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S15 · Grade B
Accurate Uncertainties for Deep Learning Using Calibrated Regression
Here, we propose a simple procedure for calibrating any regression algorithm; when applied to Bayesian and probabilistic models, it is guaranteed to produce calibrated uncertainty estimates given enough data.
2018-07-03. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S16 · Grade B
The M5 uncertainty competition: Results, findings and conclusions
To do so, the competition required the prediction of nine different quantiles (0.005, 0.025, 0.165, 0.250, 0.500, 0.750, 0.835, 0.975, and 0.995), that can sufficiently describe the complete distributions of future sales.
2022. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S17 · Grade B
Optimal Forecast Reconciliation for Hierarchical and Grouped Time Series Through Trace Minimization
Our approach minimizes the mean squared error of the coherent forecasts across the entire collection of time series under the assumption of unbiasedness.
2019. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S18 · Grade B
The accuracy of intermittent demand estimates
Intermittent demand appears sporadically, with some time periods showing no demand at all.
2005. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S19 · Grade B
On the bias of intermittent demand estimates
In addition, a modification to his method that gives approximately unbiased demand per period estimates is introduced.
2001. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S21 · Grade B
DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks
In this paper we propose DeepAR, a methodology for producing accurate probabilistic forecasts, based on training an auto regressive recurrent network model on a large number of related time series.
2019-02-22. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S24 · Grade B
Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting
The TFT also uses specialized components for the judicious selection of relevant features and a series of gating layers to suppress unnecessary components, enabling high performance in a wide range of regimes.
2020-09-27. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S25 · Grade B
Chronos: Learning the Language of Time Series
Chronos tokenizes time series values using scaling and quantization into a fixed vocabulary and trains existing transformer-based language model architectures on these tokenized time series via the cross-entropy loss.
2024-11-04. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S28 · Grade B
A hierarchical Bayesian regression model that reduces uncertainty in material demand predictions
Bayesian regression models permit the use of smaller datasets through hierarchical modeling (Vehtari et al., 2017) which allows sharing of information across heterogeneous sites.
2022-10-17. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S31 · Grade B
Preference Learning and Demand Forecast
This allows us to forecast demand in real purchase settings using inexpensive choice data with small to moderate realization probabilities.
2020. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S33 · Grade B
Rules of Machine Learning: Best Practices for ML Engineering
If there is some change that improves log loss but degrades the performance of the system, look for another feature.
2025-08-25. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S37 · Grade B
Leakage and the reproducibility crisis in machine-learning-based science
Data leakage is a spurious relationship between the independent variables and the target variable that arises as an artifact of the data collection, sampling, or pre-processing strategy.
2023-08-04. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S38 · Grade B
A Survey on Concept Drift Adaptation
Assuming a general knowledge of supervised learning in this paper we characterize adaptive learning process, categorize existing strategies for handling concept drift, discuss the most representative, distinct and popular techniques and algorithms, discuss evaluation methodology of adaptive algorithms, and present a set of illustrative applications.
2014-04-30. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S39 · Grade B
Hidden Technical Debt in Machine Learning Systems
Research solutions that provide a tiny accuracy benefit at the cost of massive increases in system complexity are rarely wise practice.
2015. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S40 · Grade B
MLOps: Continuous delivery and automation pipelines in machine learning
Therefore, you need to track summary statistics of your data and monitor the online performance of your model to send notifications or roll back when values deviate from your expectations.
2024-08-28. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S1101 · Grade B
Conformalized Quantile Regression
Conformal prediction is a technique for constructing prediction intervals that attain valid coverage in finite samples, without making distributional assumptions.
2019-05-08. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S1102 · Grade B
Probabilistic forecast reconciliation under the Gaussian framework
Forecast reconciliation of multivariate time series is the process of mapping a set of incoherent forecasts into coherent forecasts to satisfy a given set of linear constraints.
2021-03-20. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c11-S1103 · Grade B
Reconciliation of probabilistic forecasts with an application to wind power
New methods are proposed for adjusting probabilistic forecasts to ensure coherence with the aggregation constraints inherent in temporal hierarchies.
2018-08-08. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c12-S02 · Grade B
Fashion Retail: Forecasting Demand for New Items
To address this problem, we present a study of large scale fashion sales data and directly infer which clothing/footwear attributes and merchandising factors drove demand for those items.
2019-06-27. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c12-S05 · Grade B
Deep learning for new fashion product demand prediction: integrating visual similarity and demand correction in cold-start scenarios
By matching new products to these clusters, the model transfers corrected demand signals from similar historical products to estimate future demand.
2026-01-08. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c12-S06 · Grade B
Retail forecasting: research and practice
Demand estimates using only sales data would result in a negative bias in demand estimates of the focal product.
2018-11-19. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c12-S10 · Grade B
The M4 Competition: Results, findings, conclusion and way forward
The six pure ML methods performed poorly, with none of them being more accurate than the combination benchmark and only one being more accurate than Naïve2.
2018. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c12-S12 · Grade B
Another look at measures of forecast accuracy
Instead, we propose that the mean absolute scaled error become the standard measure for comparing forecast accuracy across multiple time series.
2006. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c12-S13 · Grade B
3.1. Cross-validation: evaluating estimator performance
Note that unlike standard cross-validation methods, successive training sets are supersets of those that come before them.
2026-10-30. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c12-S14 · Grade B
Strictly Proper Scoring Rules, Prediction, and Estimation
In prediction problems, proper scoring rules encourage the forecaster to make careful assessments and to be honest.
2007. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c12-S15 · Grade B
Accurate Uncertainties for Deep Learning Using Calibrated Regression
Here, we propose a simple procedure for calibrating any regression algorithm; when applied to Bayesian and probabilistic models, it is guaranteed to produce calibrated uncertainty estimates given enough data.
2018-07-03. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c12-S16 · Grade B
The M5 uncertainty competition: Results, findings and conclusions
To do so, the competition required the prediction of nine different quantiles (0.005, 0.025, 0.165, 0.250, 0.500, 0.750, 0.835, 0.975, and 0.995), that can sufficiently describe the complete distributions of future sales.
2022. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c12-S20 · Grade B
Forecast combinations: an over 50-year review
That is, equally weighted averages, which ignore past information regarding the precision of individual forecasts and correlations between forecast errors, work reasonably well compared to more sophisticated combination schemes.
2022-09-23. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c12-S32 · Grade B
Controlled experiments on the web: survey and practical guide
Controlled experiments embody the best scientific design for establishing a causal relationship between changes and their influence on user-observable behavior.
2008-07-30. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c12-S37 · Grade B
Leakage and the reproducibility crisis in machine-learning-based science
Data leakage is a spurious relationship between the independent variables and the target variable that arises as an artifact of the data collection, sampling, or pre-processing strategy.
2023-08-04. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c12-S39 · Grade B
Hidden Technical Debt in Machine Learning Systems
Research solutions that provide a tiny accuracy benefit at the cost of massive increases in system complexity are rarely wise practice.
2015. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c12-S1201 · Grade B
Evaluating time series forecasting models: An empirical study on performance estimation methods
However, in real-world scenarios, when different sources of non-stationary variation are at play, the most accurate estimates are produced by out-of-sample methods that preserve the temporal order of observations.
2019-05-28. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c12-S1202 · Grade B
Evaluating predictive count data distributions in retail sales forecasting
In addition, it is not sufficient to calculate point forecasts alone: we need to forecast entire (discrete) predictive distributions, particularly for supply chain forecasting and inventory control, but also for other planning processes.
2016. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c13-S06 · Grade B
Retail forecasting: research and practice
Demand estimates using only sales data would result in a negative bias in demand estimates of the focal product.
2018-11-19. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c13-S12 · Grade B
Another look at measures of forecast accuracy
Instead, we propose that the mean absolute scaled error become the standard measure for comparing forecast accuracy across multiple time series.
2006. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c13-S14 · Grade B
Strictly Proper Scoring Rules, Prediction, and Estimation
In prediction problems, proper scoring rules encourage the forecaster to make careful assessments and to be honest.
2007. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c13-S16 · Grade B
The M5 uncertainty competition: Results, findings and conclusions
To do so, the competition required the prediction of nine different quantiles (0.005, 0.025, 0.165, 0.250, 0.500, 0.750, 0.835, 0.975, and 0.995), that can sufficiently describe the complete distributions of future sales.
2022. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c13-S29 · Grade B
Delphi Method
Today, groups of experts or stakeholders use online tools such as ExpertLens to anonymously answer questionnaires, receive feedback that represents the “group response,” discuss, and revise their answers to see whether they can approach expert consensus.
2023-12-29. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c13-S37 · Grade B
Leakage and the reproducibility crisis in machine-learning-based science
Data leakage is a spurious relationship between the independent variables and the target variable that arises as an artifact of the data collection, sampling, or pre-processing strategy.
2023-08-04. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c13-S38 · Grade B
A Survey on Concept Drift Adaptation
Concept drift primarily refers to an online supervised learning scenario when the relation between the in- put data and the target variable changes over time.
2014-04-30. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c13-S39 · Grade B
Hidden Technical Debt in Machine Learning Systems
Research solutions that provide a tiny accuracy benefit at the cost of massive increases in system complexity are rarely wise practice.
2015. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c14-S02 · Grade B
Fashion Retail: Forecasting Demand for New Items
To our knowledge, none of these models have generalized well to predict future demand at an abstracted level for a new design/style of fashion article.
2019-06-27. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c14-S05 · Grade B
Deep learning for new fashion product demand prediction: integrating visual similarity and demand correction in cold-start scenarios
By matching new products to these clusters, the model transfers corrected demand signals from similar historical products to estimate future demand.
2026-01-08. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c14-S06 · Grade B
Retail forecasting: research and practice
Demand estimates using only sales data would result in a negative bias in demand estimates of the focal product.
2018-11-19. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c14-S07 · Grade B
FreshRetailNet-LT: A Stockout-Annotated Censored Demand Dataset for Latent Demand Recovery and Forecasting in Fresh Retail
Consequently, the sales-equals-demand assumption collapses in the event of product stockouts, as observed sales volumes systematically under-represent the latent demand.
2026-06-09. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c14-S15 · Grade B
Accurate Uncertainties for Deep Learning Using Calibrated Regression
Our procedure is inspired by Platt scaling and extends previous work on classification.
2018-07. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c14-S18 · Grade B
The accuracy of intermittent demand estimates
Intermittent demand appears sporadically, with some time periods showing no demand at all.
2005. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c14-S21 · Grade B
DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks
In retail businesses, for example, forecasting demand is crucial for having the right inventory available at the right time at the right place.
2019-02-22. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c14-S22 · Grade B
Principles and Algorithms for Forecasting Groups of Time Series: Locality and Globality
The global approach fits a single function to all series.
2021-03-26. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c14-S25 · Grade B
Chronos: Learning the Language of Time Series
We introduce Chronos, a simple yet effective framework for pretrained probabilistic time series models.
2024-11-04. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c14-S28 · Grade B
A hierarchical Bayesian regression model that reduces uncertainty in material demand predictions
Bayesian regression models permit the use of smaller datasets through hierarchical modeling (Vehtari et al., 2017) which allows sharing of information across heterogeneous sites.
2022-10-17. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c14-S32 · Grade B
Controlled experiments on the web: survey and practical guide
Controlled experiments embody the best scientific design for establishing a causal relationship between changes and their influence on user-observable behavior.
2008-07-30. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c14-S37 · Grade B
Leakage and the reproducibility crisis in machine-learning-based science
Data leakage has long been recognized as a leading cause of errors in ML applications.
2023-08-04. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c14-S38 · Grade B
A Survey on Concept Drift Adaptation
The survey aims at covering the different facets of concept drift in an integrated way to reflect on the existing scattered state-of-the-art.
2014. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c14-S39 · Grade B
Hidden Technical Debt in Machine Learning Systems
Research solutions that provide a tiny accuracy benefit at the cost of massive increases in system complexity are rarely wise practice.
2015. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c14-S1401 · Grade B
Demand Forecasting in the Fashion Industry: A Review
This is especially the case in the fashion industry, where demand uncertainty, lack of historical data and seasonal trends usually coexist.
2013. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c14-S1402 · Grade B
Preference Learning and Demand Forecast
This allows us to forecast demand in real purchase settings using inexpensive choice data with small to moderate realization probabilities.
2020-04-29. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c14-S1403 · Grade B
Strictly Proper Scoring Rules, Prediction, and Estimation
In prediction problems, proper scoring rules encourage the forecaster to make careful assessments and to be honest.
2007-03. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c14-S1404 · Grade B
Another look at measures of forecast accuracy
Instead, we propose that the mean absolute scaled error become the standard measure for comparing forecast accuracy across multiple time series.
2005-11-02. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c14-S1405 · Grade B
Optimal forecast reconciliation for hierarchical and grouped time series through trace minimization
Our approach minimizes the mean squared error of the coherent forecasts across the entire collection of time series under the assumption of unbiasedness.
2019. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗R18 · Grade B · inherited record
Inherited evidence R18
AGOA: Cameroon terminated effective 1 January 2020 for gross human-rights violations; remained ineligible; listed ineligible for calendar year 2025.
Publication date unrecorded. Inherited source-text record. The original publication has not been independently reopened for this web edition.
R27 · Grade B · inherited record
Inherited evidence R27
AI at scale in fashion: inventory cost down 35 to 40 percent; forecast accuracy up 20 to 30 percent; revenue per customer up 15 to 25 percent; forecast errors cut 20 to 50 percent; lost sales down up to 65 percent; 75 percent of executives prioritising; sector operating-profit potential US$150 to 275 billion over three to five years.
Publication date unrecorded. Inherited source-text record. The original publication has not been independently reopened for this web edition.
c01-S33 · Grade C
Rules of Machine Learning: Best Practices for ML Engineering
If there is some change that improves log loss but degrades the performance of the system, look for another feature.
2025-08-25. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c01-S40 · Grade C
MLOps: Continuous delivery and automation pipelines in machine learning
Therefore, you need to track summary statistics of your data and monitor the online performance of your model to send notifications or roll back when values deviate from your expectations.
2024-08-28. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S33 · Grade C
Rules of Machine Learning: Best Practices for ML Engineering
If there is some change that improves log loss but degrades the performance of the system, look for another feature.
2025-08-25. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c02-S40 · Grade C
MLOps: Continuous delivery and automation pipelines in machine learning
Therefore, you need to track summary statistics of your data and monitor the online performance of your model to send notifications or roll back when values deviate from your expectations.
2024-08-28. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S33 · Grade C
Rules of Machine Learning: Best Practices for ML Engineering
If there is some change that improves log loss but degrades the performance of the system, look for another feature.
2025-08-25. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c04-S40 · Grade C
MLOps: Continuous delivery and automation pipelines in machine learning
Therefore, you need to track summary statistics of your data and monitor the online performance of your model to send notifications or roll back when values deviate from your expectations.
2024-08-28. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c06-S33 · Grade C
Rules of Machine Learning: Best Practices for ML Engineering
If there is some change that improves log loss but degrades the performance of the system, look for another feature.
2025-08-25. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c07-S40 · Grade C
MLOps: Continuous delivery and automation pipelines in machine learning
Therefore, you need to track summary statistics of your data and monitor the online performance of your model to send notifications or roll back when values deviate from your expectations.
2024-08-28. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c08-S33 · Grade C
Rules of Machine Learning: Best Practices for ML Engineering
If there is some change that improves log loss but degrades the performance of the system, look for another feature.
2025-08-25. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c09-S33 · Grade C
Rules of Machine Learning: Best Practices for ML Engineering
If there is some change that improves log loss but degrades the performance of the system, look for another feature.
2025-08-25. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c10-S33 · Grade C
Rules of Machine Learning: Best Practices for ML Engineering
If there is some change that improves log loss but degrades the performance of the system, look for another feature.
2025-08-25. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c10-S40 · Grade C
MLOps: Continuous delivery and automation pipelines in machine learning
Therefore, you need to track summary statistics of your data and monitor the online performance of your model to send notifications or roll back when values deviate from your expectations.
2024-08-28. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c12-S33 · Grade C
Rules of Machine Learning: Best Practices for ML Engineering
If there is some change that improves log loss but degrades the performance of the system, look for another feature.
2025-08-25. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c13-S33 · Grade C
Rules of Machine Learning: Best Practices for ML Engineering
If there is some change that improves log loss but degrades the performance of the system, look for another feature.
2025-08-25. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗c13-S40 · Grade C
MLOps: Continuous delivery and automation pipelines in machine learning
Therefore, you need to track summary statistics of your data and monitor the online performance of your model to send notifications or roll back when values deviate from your expectations.
2024-08-28. Register access date: 2026-10-30. Source provenance is supplied by the paper evidence register.
Open the recorded source ↗R01 · Grade C · inherited record
Inherited evidence R01
Cameroon seed-cotton production 2022-2024: 330,000 t (2022), 314,455 t (2023), about 340,000 t (2024).
Publication date unrecorded. Inherited source-text record. The original publication has not been independently reopened for this web edition.
R02 · Grade C · inherited record
Inherited evidence R02
2025 seed-cotton projection above 350,000 t.
Publication date unrecorded. Inherited source-text record. The original publication has not been independently reopened for this web edition.
R03 · Grade C · inherited record
Inherited evidence R03
Company profile: more than 220,000 cotton producers supported in northern Cameroon; nine ginning plants; two oil mills.
Publication date unrecorded. Inherited source-text record. The original publication has not been independently reopened for this web edition.
R04 · Grade C · inherited record
Inherited evidence R04
SODECOTON injects roughly US$100 million a year into rural communities.
Publication date unrecorded. Inherited source-text record. The original publication has not been independently reopened for this web edition.
R05 · Grade C · inherited record
Inherited evidence R05
CFA-zone cotton output 2.3 million t in 2024/25, down 11.5 percent.
Publication date unrecorded. Inherited source-text record. The original publication has not been independently reopened for this web edition.
R06 · Grade C · inherited record
Inherited evidence R06
About 95 percent of cotton fibre exported raw against 5 percent processed locally; industrialisation target of 50 percent local processing.
Publication date unrecorded. Inherited source-text record. The original publication has not been independently reopened for this web edition.
R07 · Grade C · inherited record
Inherited evidence R07
SND30 restates the 50 percent local-processing target by 2030.
Publication date unrecorded. Inherited source-text record. The original publication has not been independently reopened for this web edition.
R08 · Grade C · inherited record
Inherited evidence R08
Announced SODECOTON and CICAM merger to create a cotton-textile industrial pole targeted by 2030.
Publication date unrecorded. Inherited source-text record. The original publication has not been independently reopened for this web edition.
R09 · Grade C · inherited record
Inherited evidence R09
Camtext SA integrated cotton-to-textile project, US$300 million (180 billion XAF); Panafritex and Arise with SODECOTON, CNPS and Marlo; 12 November 2025.
Publication date unrecorded. Inherited source-text record. The original publication has not been independently reopened for this web edition.
R10 · Grade C · inherited record
Inherited evidence R10
Camtext SA: 12,000 t a year processed; about 12,000 jobs at the Dibamba hub and 3,000 at Garoua; return on investment near 11 years; optimal capacity around 2033.
Publication date unrecorded. Inherited source-text record. The original publication has not been independently reopened for this web edition.
R11 · Grade C · inherited record
Inherited evidence R11
CICAM market share from about 85 percent three decades ago to about 5 percent today.
Publication date unrecorded. Inherited source-text record. The original publication has not been independently reopened for this web edition.
R12 · Grade C · inherited record
Inherited evidence R12
CICAM capacity utilisation, July 2023 report: Garoua 33.7 percent, CICAM 1 48.9 percent, CICAM 2 10.83 percent; underutilisation cost about CFAF 2 billion in 2020.
Publication date unrecorded. Inherited source-text record. The original publication has not been independently reopened for this web edition.
R13 · Grade C · inherited record
Inherited evidence R13
CICAM restructuring cost estimate CFAF 30.7 to 48.2 billion; one relaunch plan cited at 70.2 billion.
Publication date unrecorded. Inherited source-text record. The original publication has not been independently reopened for this web edition.
R14 · Grade C · inherited record
Inherited evidence R14
Cameroon minimum wage (SMIG) XAF 41,875 a month in 2023, raised to XAF 43,969 a month from 23 February 2024, about US$76, a rise of 5 percent.
Publication date unrecorded. Inherited source-text record. The original publication has not been independently reopened for this web edition.
R15 · Grade C · inherited record
Inherited evidence R15
Average salary across sectors in Cameroon about US$359 a month.
Publication date unrecorded. Inherited source-text record. The original publication has not been independently reopened for this web edition.
R16 · Grade C · inherited record
Inherited evidence R16
Informal share of employment about 90 percent; standard 40-hour week, 48-hour maximum, overtime at 1.2 times.
Publication date unrecorded. Inherited source-text record. The original publication has not been independently reopened for this web edition.
R23 · Grade C · inherited record
Inherited evidence R23
Textiles and clothing among unresolved AfCFTA tariff-line categories; 92.3 percent of lines agreed excluding vehicles, textiles and clothing.
Publication date unrecorded. Inherited source-text record. The original publication has not been independently reopened for this web edition.
R24 · Grade C · inherited record
Inherited evidence R24
Africa textile market about US$37.3 billion in 2025, projected US$49.41 billion by 2030 at 4.73 percent a year.
Publication date unrecorded. Inherited source-text record. The original publication has not been independently reopened for this web edition.
R25 · Grade C · inherited record
Inherited evidence R25
Africa textile market to about US$72.7 billion by 2035 at 6.9 percent a year; fashion and apparel 48.1 percent of the market in 2024.
Publication date unrecorded. Inherited source-text record. The original publication has not been independently reopened for this web edition.
R26 · Grade C · inherited record
Inherited evidence R26
Cameroon clothing and footwear spend about US$94.70 a person in 2024 and about 8.0 pieces a person; apparel eCommerce revenue US$20.32 million (2023) to US$33.61 million (2027) at 13.41 percent a year; user penetration 18.0 percent (2023) to 22.7 percent (2027).
Publication date unrecorded. Inherited source-text record. The original publication has not been independently reopened for this web edition.
R29 · Grade C · inherited record
Inherited evidence R29
Manual defect inspection 60 to 70 percent accurate, missing 20 to 30 percent of defects; computer vision above 90 percent across more than 40 defect types; line-scan inspection up to 60 metres a minute.
Publication date unrecorded. Inherited source-text record. The original publication has not been independently reopened for this web edition.
R32 · Grade C · inherited record
Inherited evidence R32
CFA franc to US dollar reference rates; franc pegged to the euro at 655.957. The GFT study's method note places the franc near 590 to 610 per US dollar across the 2023 study window and near 563 to 577 more recently, and treats currency conversions as estimates.
Publication date unrecorded. Inherited source-text record. The original publication has not been independently reopened for this web edition.
Keep the definitions stable
47 terms, each with one definition for the whole paper. The punched row shows the chapters whose text uses the term.
Recurs inreading guide, not a citation
Cut to length
Chapters 01 to 02 fit in 60 minutes, with 5 minutes to spare.
Start chapter 01 · 2 chapters in 60 minWP04 · Draft web edition
Forecasting From a Cold Start
Cut length 2 chapters · 55 min
The PDF has passed its publication gates: 257 rendered A4 pages, 1.9 MB.
Download the verified PDFOn the same rack
WP01The Local-Processing GapWP02Measure Before You ModelWP12Inventory as a DecisionRelated tools: Cold-start demand-forecast lab, Capacity and utilisation ramp planner, KPI cascade builder
Issued by Green Future Tech Limited, Hong Kong SAR. This research is not investment, legal or tax advice. Illustrative calculations require local validation before an operating or financing decision.