Machine Learning Methods and Hybrid Models in Supply Chain Forecasting
Marek LEWIŃSKI, Katarzyna A. MŁYNARCZYK
Abstract. Supply chain forecasting is a broad domain embracing number of topics like demand planning, pricing, supply and service prediction. It is also an integral part of many processes that those affect. This paper describes machine learning methods used in forecasting like regressions, random forest, XGBoost but also showcases the newest contributions to deep learning architectures used for forecasting like RNNs, LSTMs as well as state-of-art Transformer models created for long-term forecasting: TimeGPT and PatchTST. Paper also describes another robust approach for time series forecasting – hybrid approaches that combine both statistical and machine learning models alongside their applications.
Keywords
Machine Learning, Forecasting, Supply Chain Forecasting, Deep Learning, Transformers, Hybrid Models
Published online 1/25/2026, 6 pages
Copyright © 2026 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA
Citation: Marek LEWIŃSKI, Katarzyna A. MŁYNARCZYK, Machine Learning Methods and Hybrid Models in Supply Chain Forecasting, Materials Research Proceedings, Vol. 62, pp 222-227, 2026
DOI: https://doi.org/10.21741/9781644904015-29
The article was published as article 29 of the book Terotechnology XIV
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
References
[1] M. Lewiński, S.A. Lariane, Statistical Forecasting Methods and Machine Learning Models in Hierarchical Forecasting for Supply Chain Applications, Materials Research Proceedings 45 (2024) 286-295. https://doi.org/10.21741/9781644903315-33
[2] F. Petropoulos et al., Forecasting: theory and practice, International Journal of Forecasting 38 (2022) 705-871. https://doi.org/10.1016/j.ijforecast.2021.11.001
[3] R.J. Hyndman, G. Athanasopoulos, Forecasting: principles and practice, 3rd Ed., OTexts, Melbourne, Australia, 2021. http://OTexts.com/fpp3. Accessed on 2025-07-31.
[4] R.P. Masini, M.C. Medeiros, Machine Learning Advances for Time Series Forecasting, arXiv:2012.12802 [econ.EM], https://doi.org/10.48550/arXiv.2012.12802
[5] T. Chen, C. Guestrin, XGBoost: A Scalable Tree Boosting System, in: Proc. 22nd ACM SIGKDD Int. Conf. Knowl. Discovery and Data Mining (KDD ’16). Association for Computing Machinery, New York, NY, USA, 2016, 785–794. https://doi.org/10.1145/2939672.2939785
[6] S. Hochreiter, J. Schmidhuber, Long Short-Term Memory. Neural Comput. 9 (1997) 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735
[7] B.N. Oreshkin et al., N-BEATS: Neural basis expansion analysis for interpretable time series forecasting, arXiv:1905.10437 [cs.LG], https://doi.org/10.48550/arXiv.1905.10437
[8] C. Challu et al., N-HiTS: Neural Hierarchical Interpolation for Time Series Forecasting, arXiv:2201.12886 [cs.LG], https://doi.org/10.48550/arXiv.2201.12886
[9] S. Makridakis et al., The M4 Competition: Results, findings, conclusion and way forward, Int. J. Forecasting 34 (2018) 802-808. https://doi.org/10.1016/j.ijforecast.2018.06.001
[10] Ü.Ç. Büyükşahin, Ş. Ertekin, Improving forecasting accuracy of time series data using a new ARIMA-ANN hybrid method and empirical mode decomposition, Neurocomputing 361 (2019) 151-163. https://doi.org/10.1016/j.neucom.2019.05.099
[11] P. Li, J.-S. Zhang, A New Hybrid Method for China’s Energy Supply Security Forecasting Based on ARIMA and XGBoost. Energies, Vol. 11, 2018, https://doi.org/10.3390/en11071687.
[12] W. Tingyu, L. Wenyang, X. Jun, Supply chain sales forecasting based on lightGBM and LSTM combination model, Industrial Management & Data Systems 120 (2020) 265-279. https://doi.org/10.1108/IMDS-03-2019-0170.
[13] X. Wang et al., Forecast combinations: An over 50-year review, Int. J. Forecasting 39 (2023) 1518-1547. https://doi.org/10.1016/j.ijforecast.2022.11.005
[14] J. Kim et al. A comprehensive survey of deep learning for time series forecasting: architectural diversity and open challenges, Artif. Intell. Rev. 58 (2025) art.216. https://doi.org/10.1007/s10462-025-11223-9
[15] A. Garza et al., TimeGPT-1, arXiv:2310.03589 [cs.LG], https://doi.org/10.48550/arXiv.2310.03589
[16] Y. Nie et al., A Time Series is Worth 64 Words: Long-term Forecasting with Transformers, arXiv:2211.14730 [cs.LG], https://doi.org/10.48550/arXiv.2211.14730.
[17] A. Zeng et al., Are Transformers Effective for Time Series Forecasting?,
arXiv:2205.13504 [cs.AI], https://doi.org/10.48550/arXiv.2205.13504.
[18] K. Douaioui et al., Machine Learning and Deep Learning Models for Demand Forecasting in Supply Chain Management: A Critical Review. Appl. Syst. Innov. 7 (2024) art.93. https://doi.org/10.3390/asi7050093
[19] M.Z. Babai et al., On the use of machine learning in supply chain management: a systematic review, IMA J. Manag. Mathematics 36 (2025) 21-49. https://doi.org/10.1093/imaman/dpae029
[20] S.R. Haque, Machine Learning Applications in End-To-End Supply Chain Management: A Comprehensive Review, Int. J. Sci. Res. Manag. 13 (2025) 2226-2241. https://doi.org/10.18535/ijsrm/v13i06.ec03
