Stockout-Aware Relational Demand Forecasting and Cross-Dataset Error Trade-offs
DOI:
https://doi.org/10.51903/jtie.v4i1.594Keywords:
stockout-censored demand, latent-demand recovery, retail forecasting, relational learning, global forecastingAbstract
Retail sales are a censored view of demand when products become unavailable. This study evaluates profile-weighted temporal reconstruction and relational forecasting on FreshRetailNet-50K, then examines cross-dataset error tradeoffs on M5. FreshRetailNet contains 50,000 store–product series, 4.85 million daily records, hourly sales, and stockout labels. Category-hour profiles estimate missing intraday shares, while a trailing 28-row own-series prior supplies the demand scale. Artificial contiguous-hour masking on days without labeled open-hour stockouts yields reconstruction WAPE of 8.82%–21.32%; it does not validate natural-stockout demand recovery. On 206,562 observable rows in the seven-day official test, calibrated relational forecasting achieves RMSE 0.6761, MAE 0.3621, and WAPE 29.27%, versus 30.54% for observed-sales boosting. Recovery alone does not improve WAPE, and the incremental graph contribution is small. Two earlier seven-day windows support the direction of the calibrated comparison but do not assess seasonal stability. M5 evaluation covers 30,490 series and 28 rolling one-day-ahead origins. Fixed-budget 1:1 pooling lowers relational-model RMSE from 2.1075 to 2.0716, while increasing WAPE from 71.67% to 72.21%. Alternative sampling ratios and full-target augmentation show the same metric tradeoff. Dense series receive the strongest squared-error benefit, without a WAPE advantage. The findings distinguish controlled reconstruction accuracy from observable-sales prediction and show that cross-retailer pooling does not uniformly improve forecasting.
References
Ban, G.-Y. (2020). Confidence intervals for data-driven inventory policies with demand censoring. Operations Research, 68(2), 309–326. https://doi.org/10.1287/opre.2019.1883
Besbes, O., & Muharremoglu, A. (2013). On implications of demand censoring in the newsvendor problem. Management Science, 59(6), 1407–1424. https://doi.org/10.1287/mnsc.1120.1654
Croston, J. D. (1972). Forecasting and stock control for intermittent demands. Operational Research Quarterly, 23(3), 289–303. https://doi.org/10.1057/jors.1972.50
Demšar, J. (2006). Statistical comparisons of classifiers over multiple data sets. Journal of Machine Learning Research, 7(1), 1–30. https://jmlr.org/papers/v7/demsar06a.html
Ding, J., Huh, W. T., & Rong, Y. (2024). Feature-based inventory control with censored demand. Manufacturing & Service Operations Management, 26(3), 1157–1172. https://doi.org/10.1287/msom.2021.0135
Ding, X., Puterman, M. L., & Bisi, A. (2002). The censored newsvendor and the optimal acquisition of information. Operations Research, 50(3), 517–527. https://doi.org/10.1287/opre.50.3.517.7752
Dingdong-Inc. (2025). FreshRetailNet-50K (Version 1.0) [Data set]. Hugging Face. https://huggingface.co/datasets/Dingdong-Inc/FreshRetailNet-50K
Fildes, R., Ma, S., & Kolassa, S. (2022). Retail forecasting: Research and practice. International Journal of Forecasting, 38(4), 1283–1318. https://doi.org/10.1016/j.ijforecast.2019.06.004
Ganin, Y., Ustinova, E., Ajakan, H., Germain, P., Larochelle, H., Laviolette, F., Marchand, M., & Lempitsky, V. (2016). Domain-adversarial training of neural networks. Journal of Machine Learning Research, 17(59), 1–35. https://jmlr.org/papers/v17/15-239.html
Goltsos, T. E., Syntetos, A. A., Glock, C. H., & Ioannou, G. (2022). Inventory–forecasting: Mind the gap. European Journal of Operational Research, 299(2), 397–419. https://doi.org/10.1016/j.ejor.2021.07.040
Huh, W. T., & Rusmevichientong, P. (2009). A nonparametric asymptotic analysis of inventory planning with censored demand. Mathematics of Operations Research, 34(1), 103–123. https://doi.org/10.1287/moor.1080.0355
Hyndman, R. J., Ahmed, R. A., Athanasopoulos, G., & Shang, H. L. (2011). Optimal combination forecasts for hierarchical time series. Computational Statistics & Data Analysis, 55(9), 2579–2589. https://doi.org/10.1016/j.csda.2011.03.006
Hyndman, R. J., & Koehler, A. B. (2006). Another look at measures of forecast accuracy. International Journal of Forecasting, 22(4), 679–688. https://doi.org/10.1016/j.ijforecast.2006.03.001
Jain, A., Rudi, N., & Wang, T. (2015). Demand estimation and ordering under censoring: Stock-out timing is (almost) all you need. Operations Research, 63(1), 134–150. https://doi.org/10.1287/opre.2014.1326
Kaplan, E. L., & Meier, P. (1958). Nonparametric estimation from incomplete observations. Journal of the American Statistical Association, 53(282), 457–481. https://doi.org/10.1080/01621459.1958.10501452
Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., & Liu, T.-Y. (2017). LightGBM: A highly efficient gradient boosting decision tree. In I. Guyon, U. von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, & R. Garnett (Eds.), Advances in neural information processing systems (Vol. 30, pp. 3146–3154). Curran Associates. https://papers.nips.cc/paper/6907-lightgbm-a-highly-efficient-gradient-boosting-decision-tree
Lu, X., Song, J.-S., & Zhu, K. (2008). Analysis of perishable-inventory systems with censored demand data. Operations Research, 56(4), 1034–1038. https://doi.org/10.1287/opre.1080.0553
Makridakis, S., Spiliotis, E., & Assimakopoulos, V. (2022a). M5 accuracy competition: Results, findings, and conclusions. International Journal of Forecasting, 38(4), 1346–1364. https://doi.org/10.1016/j.ijforecast.2021.11.013
Makridakis, S., Spiliotis, E., & Assimakopoulos, V. (2022b). The M5 competition: Background, organization, and implementation. International Journal of Forecasting, 38(4), 1325–1336. https://doi.org/10.1016/j.ijforecast.2021.07.007
Mersereau, A. J. (2015). Demand estimation from censored observations with inventory record inaccuracy. Manufacturing & Service Operations Management, 17(3), 335–349. https://doi.org/10.1287/msom.2015.0520
Montero-Manso, P., & Hyndman, R. J. (2021). Principles and algorithms for forecasting groups of time series: Locality and globality. International Journal of Forecasting, 37(4), 1632–1653. https://doi.org/10.1016/j.ijforecast.2021.03.004
Pan, S. J., & Yang, Q. (2010). A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359. https://doi.org/10.1109/TKDE.2009.191
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., & Duchesnay, É. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12, 2825–2830. https://jmlr.org/papers/v12/pedregosa11a.html
Semenoglou, A.-A., Spiliotis, E., Makridakis, S., & Assimakopoulos, V. (2021). Investigating the accuracy of cross-learning time series forecasting methods. International Journal of Forecasting, 37(3), 1072–1084. https://doi.org/10.1016/j.ijforecast.2020.11.009
Shi, C., Chen, W., & Duenyas, I. (2016). Technical Note—Nonparametric data-driven algorithms for multiproduct inventory systems with censored demand. Operations Research, 64(2), 362–370. https://doi.org/10.1287/opre.2015.1474
Snyder, R. D., Ord, J. K., & Beaumont, A. N. (2012). Forecasting the intermittent demand for slow-moving inventories: A modelling approach. International Journal of Forecasting, 28(2), 485–496. https://doi.org/10.1016/j.ijforecast.2011.03.009
Syntetos, A. A., & Boylan, J. E. (2005). The accuracy of intermittent demand estimates. International Journal of Forecasting, 21(2), 303–314. https://doi.org/10.1016/j.ijforecast.2004.10.001
Teunter, R. H., Syntetos, A. A., & Babai, M. Z. (2011). Intermittent demand: Linking forecasting to inventory obsolescence. European Journal of Operational Research, 214(3), 606–615. https://doi.org/10.1016/j.ejor.2011.05.018
Tobin, J. (1958). Estimation of relationships for limited dependent variables. Econometrica, 26(1), 24–36. https://doi.org/10.2307/1907382
University of Nicosia. (2020). M5 forecasting—Accuracy [Data set]. Kaggle. https://www.kaggle.com/competitions/m5-forecasting-accuracy
Wang, J., Xin, Q., Liu, Y., Wang, J., & Yang, T. (2024). Predicting enterprise marketing decision making with intelligent data-driven approaches. Journal of Industrial Engineering and Applied Science, 2(3), 12–19. https://doi.org/10.5281/zenodo.11357252
Wang, Y., Gu, J., Long, L., Li, X., Shen, L., Fu, Z., Zhou, X., & Jiang, X. (2025). FreshRetailNet-50K: A stockout-annotated censored demand dataset for latent demand recovery and forecasting in fresh retail (Version 1) [Preprint]. arXiv. https://arxiv.org/abs/2505.16319v1
Wecker, W. E. (1978). Predicting demand from sales data in the presence of stockouts. Management Science, 24(10), 1043–1054. https://doi.org/10.1287/mnsc.24.10.1043
Wellens, A. P., Boute, R. N., & Udenio, M. (2024). Simplifying tree-based methods for retail sales forecasting with explanatory variables. European Journal of Operational Research, 314(2), 523–539. https://doi.org/10.1016/j.ejor.2023.10.039
Wellens, A. P., Udenio, M., & Boute, R. N. (2022). Transfer learning for hierarchical forecasting: Reducing computational efforts of M5 winning methods. International Journal of Forecasting, 38(4), 1482–1491. https://doi.org/10.1016/j.ijforecast.2021.09.011
Wickramasuriya, S. L., Athanasopoulos, G., & Hyndman, R. J. (2019). Optimal forecast reconciliation for hierarchical and grouped time series through trace minimization. Journal of the American Statistical Association, 114(526), 804–819. https://doi.org/10.1080/01621459.2018.1448825
Wu, Z., Pan, S., Long, G., Jiang, J., Chang, X., & Zhang, C. (2020). Connecting the dots: Multivariate time series forecasting with graph neural networks. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (pp. 753–763). Association for Computing Machinery. https://doi.org/10.1145/3394486.3403118
Wu, Z., Pan, S., Long, G., Jiang, J., & Zhang, C. (2019). Graph WaveNet for deep spatial-temporal graph modeling. In Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (pp. 1907–1913). International Joint Conferences on Artificial Intelligence Organization. https://doi.org/10.24963/ijcai.2019/264
Zhang, H. (2023). DriftGuard: Multi-signal drift early warning and safe re-training/rollback for CTR/CVR models. Journal of Advanced Computing Systems, 3(7), 24–40. https://doi.org/10.69987/JACS.2023.30703
Downloads
Published
Data Availability Statement
FreshRetailNet-50K is available from Dingdong-Inc on Hugging Face (Dingdong-Inc, 2025). M5 sales, calendar, and price data are available through the M5 Forecasting—Accuracy competition (University of Nicosia, 2020). The accompanying supplementary analysis package contains the experiment scripts, input-file checksums, fitted models, prediction outputs, summary tables, and figure-generation code. The two benchmarks retain their distinct roles: FreshRetailNet supplies hourly availability labels, whereas M5 supplies observed sales only.
Issue
Section
License
Copyright (c) 2025 Mengyi Chen, Jeffrey Jin
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
