Abstract
Intermittent demand forecasting remains a fundamental challenge in large-scale supply chains due to extreme demand sparsity, irregular occurrence patterns, and highly variable demand magnitudes. While recent studies have increasingly adopted complex multi-stage model architectures to address these challenges, the role of statistically grounded feature engineering has received comparatively less attention. This study proposes the Smoothed Hybrid Occurrence-Size (SHOS) framework, which generates adaptive, series-specific estimates of demand occurrence probability and conditional demand size using sparsity-aware exponential smoothing. These estimates are incorporated as features into supervised machine learning models trained on large-scale, zero-padded panel data. The proposed approach is evaluated on an automotive aftermarket dataset comprising approximately 1.4 million monthly observations across 56,000 spare-part time series, using an 11-fold rolling-window cross-validation protocol. Empirical results demonstrate that SHOS-enhanced models achieve substantial performance improvements over baseline feature sets, reducing mean absolute error (MAE) by approximately 50% and weighted mean absolute percentage error (WMAPE) by over 40% in highly intermittent demand segments. Notably, despite their increased architectural complexity, two-stage hurdle-based models do not outperform the proposed single-stage SHOS-enhanced framework. Formal statistical testing using the Wilcoxon signed-rank test confirms that the performance advantage of the single-stage SHOS model is consistent and statistically significant across all validation folds (p < 0.001). These findings reveal an unexpected but practically important insight: robust, statistically informed feature engineering can be more effective than increased model complexity for intermittent demand forecasting. The results highlight the value of simple, interpretable, and computationally efficient forecasting frameworks for large-scale operational deployment, while motivating future validation across additional application domains.
Similar content being viewed by others
Data availability
All the data and material used in this study is available in the manuscript, and further details if required, the corresponding author will provide the same, through proper requisition.
References
Nikolopoulos, K. We need to talk about intermittent demand forecasting. Eur. J. Oper. Res. 291, 549–559. https://doi.org/10.1016/j.ejor.2019.12.046 (2021).
Kourentzes, N. & Athanasopoulos, G. Elucidate structure in intermittent demand series. Eur. J. Oper. Res. 288, 141–152. https://doi.org/10.1016/j.ejor.2020.05.046 (2021).
Pinçe, Ç., Turrini, L. & Meissner, J. Intermittent demand forecasting for spare parts: A critical review. Omega (United Kingdom). 105, 102513. https://doi.org/10.1016/j.omega.2021.102513 (2021).
J. D. Croston. Forecasting and stock control for intermittent demands. Oper. Res. Q. 23, 289–303 (1972).
Syntetos, A. A. & Boylan, J. E. The accuracy of intermittent demand estimates. Int. J. Forecast. 21, 303–314. https://doi.org/10.1016/j.ijforecast.2004.10.001 (2005).
Teunter, R. H., Syntetos, A. A. & Babai, M. Z. Intermittent demand: Linking forecasting to inventory obsolescence. Eur. J. Oper. Res. 214 (3), 606–615. https://doi.org/10.1016/j.ejor.2011.05.018 (2011).
Ke, G. et al. T.-Y. Liu. LightGBM: A highly efficient gradient boosting decision tree. In Advances in Neural Information Processing Systems. Vol. 30. 3146–3154 (Curran Associates, Inc., 2017).
Chen, T. C. Guestrin. XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 785–794. https://doi.org/10.1145/2939672.2939785 (ACM, 2016).
Babai, M. Z., Arampatzis, M., Hasni, M., Lolli, F. & Tsadiras, A. On the use of machine learning in supply chain management: A systematic review. IMA J. Manag. Math. 36, 21–49. https://doi.org/10.1093/imaman/dpae029 (2025).
Gutierrez, R. S., Solis, A. O. & Mukhopadhyay, S. Lumpy demand forecasting using neural networks. Int. J. Prod. Econ. 111, 409–420. https://doi.org/10.1016/j.ijpe.2007.01.007 (2008).
Makridakis, S., Spiliotis, E. & Assimakopoulos, V. The M4 competition: Results, findings, conclusion and way forward. Int. J. Forecast. 34, 802–808. https://doi.org/10.1016/j.ijforecast.2018.06.001 (2018).
Makridakis, S. et al. The M5 competition: Background, organization, and implementation. Int. J. Forecast. 38, 1325–1336. https://doi.org/10.1016/j.ijforecast.2021.07.007 (2022).
Syntetos, A. A. & Boylan, J. E. On the bias of intermittent demand estimates. Int. J. Prod. Econ. 71, 457–466. https://doi.org/10.1016/S0925-5273(00)00143-2 (2001).
Eaves, A. H. C. & Kingsman, B. G. Forecasting for the ordering and stock-holding of spare parts. J. Oper. Res. Soc. 55, 431–437. https://doi.org/10.1057/palgrave.jors.2601697 (2004).
Teunter, R. H., Syntetos, A. A. & Babai, M. Z. Intermittent demand: Linking forecasting to inventory obsolescence. Eur. J. Oper. Res. 214, 606–615. https://doi.org/10.1016/j.ejor.2011.05.018 (2011).
Zhang, G., Patuwo, B. E. & Hu, M. Y. Forecasting with artificial neural networks: The state of the art. Int. J. Forecast. 14 (1), 35–62. https://doi.org/10.1016/S0169-2070(97)00044-7 (1998).
Smyl, S. A hybrid method of exponential smoothing and recurrent neural networks for time series forecasting. Int. J. Forecast. 36, 75–85. https://doi.org/10.1016/j.ijforecast.2019.03.017 (2020).
Li, L., Kang, Y., Petropoulos, F. & Li, F. Feature-based intermittent demand forecast combinations: Accuracy and inventory implications. Int. J. Prod. Res. 61, 7557–7572. https://doi.org/10.1080/00207543.2022.2153941 (2023).
Ma, T., Lin, Y., Zhou, X. & Zhang, M. Grading evaluation of goaf stability based on entropy and normal cloud model. Adv. Civil Eng. 2022 (1), 9600909. https://doi.org/10.1155/2022/9600909 (2022).
Xu, B. et al. Study on the prediction of the uniaxial compressive strength of rock based on the SSA-XGBoost model. Sustainability 15 (6), 5201. https://doi.org/10.3390/su15065201 (2023).
Cheng, Y. et al. Hybrid data-driven model and Shapley additive explanations for peak dilation angle of rock discontinuities. Mater. Today Commun. 40, 110194. https://doi.org/10.1016/j.mtcomm.2024.110194 (2024).
Ma, T. et al. Elastic modulus prediction for high-temperature treated rock using multi-step hybrid ensemble model combined with coronavirus herd immunity optimizer. Measurement 240, 115596. https://doi.org/10.1016/j.measurement.2024.115596 (2025).
Ma, T. et al. Physics-informed neural networks for capturing the true relationships between parameters to predict the dynamic triaxial strength of rocks in cold environments. Measurement 118900. https://doi.org/10.1016/j.measurement.2025.118900 (2025).
Shen, L. et al. A new CNN-GRU deep learning framework optimized by CHIO for precise prediction of debris flow velocity. Stoch. Environ. Res. Risk Assess. 1–21. https://doi.org/10.1007/s00477-025-02973-7 (2025).
Ma, T. et al. Hybrid empirical-data-driven neural network for predicting air-entry value in unsaturated soils. Math. Geosci. 1–30. https://doi.org/10.1007/s11004-025-10230-4 (2025).
Liu, H. et al. Deep learning in rockburst intensity level prediction: performance evaluation and comparison of the NGO-CNN-BiGRU-attention model. Appl. Sci. 14 (13), 5719. https://doi.org/10.3390/app14135719 (2024).
Wang, Y., Ma, T., Shen, L., Wang, X. & Luo, R. Prediction of thermal conductivity of natural rock materials using LLE-transformer-lightGBM model for geothermal energy applications. Energy Rep. 13, 2516–2530. https://doi.org/10.1016/j.egyr.2025.02.003 (2025).
Xie, S., Lin, H., Ma, T., Peng, K. & Sun, Z. Prediction of joint roughness coefficient via hybrid machine learning model combined with principal components analysis. J. Rock Mech. Geotech. Eng. 17 (4), 2291–2306. https://doi.org/10.1016/j.jrmge.2024.05.059 (2025).
Nathan, B. S., Reddy, S., Sastry, B. V., Krishnaiah, C. C., Eswaramoorthy, K. V. & J., & Innovative framework for effective service parts management in the automotive industry. Front. Mech. Eng. 10, 1361688. https://doi.org/10.3389/fmech.2024.1361688 (2024).
B, S. N. et al. A machine learning framework for long-term forecasting of spare part demand in end-of-life product scenarios. Sci. Rep. https://doi.org/10.1038/s41598-025-31171-2 (2025).
Bobbili, V. S. R. et al. Physics-informed neural networks for predicting high-strain-rate energy absorption in additively manufactured lattice materials. Progress Additive Manuf. 1–27. https://doi.org/10.1007/s40964-025-01460-3 (2025).
Reddy, B. V. S. et al. Machine learning approaches for predicting mechanical properties in additive manufactured lattice structures. Mater. Today Commun. 40, 109937. https://doi.org/10.1016/j.mtcomm.2024.109937 (2024).
Reddy, B. V. S. et al. Performance evaluation of machine learning techniques in surface roughness prediction for 3D printed micro-lattice structures. J. Manuf. Process. 137, 320–341. https://doi.org/10.1016/j.jmapro.2025.01.082 (2025).
Lichman, M. P. Smyth. Prediction of sparse user-item consumption rates with zero-inflated poisson regression In The Web Conference - Proceedings of the World Wide Web Conference, WWW 2018. 719–728. https://doi.org/10.1145/3178876.3186153 (ACM, 2018).
Wallström, P. & Segerstedt, A. Evaluation of forecasting error measurements and techniques for intermittent demand. Int. J. Prod. Econ. 128, 625–636. https://doi.org/10.1016/j.ijpe.2010.07.013 (2010).
Cameron, A. C. & Trivedi, P. K. Regression Analysis of Count Data (Cambridge University Press, 2012).
Kourentzes, N. On intermittent demand model optimisation and selection. Int. J. Prod. Econ. 156, 180–190. https://doi.org/10.1016/j.ijpe.2014.06.007 (2014).
Funding
This work was co-funded by the European Union under the REFRESH - Research Excellence for Region Sustainability and High-tech Industries project (Project No. CZ.10.03.01/00/22_003/0000048) via the Operational Programme Just Transition. This article was also supported by the Students Grant Competition SP2024/087, Specific Research of Sustainable Manufacturing Technologies, financed by the Ministry of Education, Youth and Sports (MEYS), Czech Republic, and the Faculty of Mechanical Engineering, VŠB-Technical University of Ostrava.
Author information
Authors and Affiliations
Contributions
S. N. B.: Conceptualization (equal); Data curation (lead); Formal analysis (lead); Investigation (equal); Methodology (equal); Writing-original draft (lead); Writing-review & editing (equal). (A) P. M.: Conceptualization (equal); Methodology (equal); Formal analysis (lead); Investigation (equal); Writing & editing (equal). (B) V. S. R.: Conceptualization (equal); Data curation (lead); Formal analysis (lead); Investigation (equal); Methodology (equal); Writing-original draft (lead); Writing & editing (equal). (C) C. S.: Conceptualization (equal); Methodology (equal); Formal analysis (lead); Funding acquisition (lead); Supervision (lead); Investigation (equal); Writing & editing (lead). S. S.: Funding acquisition (lead); Investigation (equal); Writing & editing (equal). R. C.: Funding acquisition (lead); Investigation (equal); Writing & editing (equal).
Corresponding authors
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Nathan, B.S., Aravinth, P.M., Reddy, B.V.S. et al. Primacy of feature engineering over architectural complexity for intermittent demand forecasting. Sci Rep (2026). https://doi.org/10.1038/s41598-026-35197-y
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-35197-y
