Causal Machine Learning Approaches for Interpretable Demand Forecasting in Supply Chain Analytics
Keywords:
Causal Inference, Interpretability, Demand Forecasting, Supply Chain Analytics, Machine Learning, RobustnessAbstract
Demand forecasting in modern supply chain analytics faces profound challenges from nonlinear dependencies, latent confounders, and structural interventions such as promotions, disruptions, and policy shifts. Conventional machine learning models, while achieving high predictive accuracy, often function as opaque black boxes that fail to disentangle correlation from causation, thereby limiting their interpretability and robustness under distributional shifts. This paper advances a systems-level framework that integrates causal inference principles with machine learning architectures to produce interpretable demand forecasts that support strategic decision-making. We systematically review the landscape of causal machine learning approaches, including heterogeneous treatment effect estimators, structural causal models, and doubly robust methods, and examine their applicability to supply chain contexts. The discussion emphasizes critical trade-offs between predictive performance, causal identifiability, model complexity, and computational scalability. Architectural considerations such as feature engineering under confounding, model selection for causal effect estimation, and the role of domain knowledge in constructing directed acyclic graphs are explored in depth. Deployment challenges, including data infrastructure requirements, online updating, governance of algorithmic decisions, and sustainability of inference under evolving supply networks, are analyzed from a socio-technical perspective. The paper further draws cross-domain comparisons with healthcare and economics to highlight transferable design principles. Through illustrative cases, we demonstrate how causal machine learning enhances interpretability by providing counterfactual explanations and scenario analyses that are actionable for planners. The conclusion underscores the necessity of embedding causal reasoning into the forecasting pipeline to achieve resilience, fairness, and long-term operational alignment in supply chain systems.
References
1. Makridakis, S., Spiliotis, E., & Assimakopoulos, V. (2018). Statistical and machine learning forecasting methods: Concerns and ways forward. PLOS ONE, 13(3), e0194889.
2. Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32.
3. Pearl, J. (2009). Causality: Models, reasoning, and inference (2nd ed.). Cambridge University Press.
4. Imbens, G. W., & Rubin, D. B. (2015). Causal inference for statistics, social, and biomedical sciences: An introduction. Cambridge University Press.
5. Athey, S., & Imbens, G. W. (2016). Recursive partitioning for heterogeneous causal effects. Proceedings of the National Academy of Sciences, 113(27), 7353–7360.
6. Shmueli, G. (2010). To explain or to predict? Statistical Science, 25(3), 289–310.
7. Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). “Why should I trust you?”: Explaining the predictions of any classifier. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 1135–1144.
8. Künzel, S. R., Sekhon, J. S., Bickel, P. J., & Yu, B. (2019). Metalearners for estimating heterogeneous treatment effects using machine learning. Proceedings of the National Academy of Sciences, 116(10), 4156–4165.
9. Bang, H., & Robins, J. M. (2005). Doubly robust estimation in missing data and causal inference models. Biometrics, 61(4), 962–973.
10. Peters, J., Janzing, D., & Schölkopf, B. (2017). Elements of causal inference: Foundations and learning algorithms. MIT Press.
11. Johansson, F. D., Shalit, U., & Sontag, D. (2016). Learning representations for counterfactual inference. Proceedings of the 33rd International Conference on Machine Learning, 3020–3029.
12. Kyono, T., Zhang, Y., & van der Schaar, M. (2020). CASTLE: Regularization via auxiliary causal graph. Proceedings of the 37th International Conference on Machine Learning, 5524–5534.
13. Lim, B., & Zohren, S. (2021). Time-series forecasting with deep learning: A survey. Philosophical Transactions of the Royal Society A, 379(2194), 20200209.
14. Arjovsky, M., Bottou, L., Gulrajani, I., & Lopez-Paz, D. (2019). Invariant risk minimization. arXiv preprint arXiv:1907.02893.
15. Mitchell, M., Wu, S., Zaldivar, A., Barnes, P., Vasserman, L., Hutchinson, B., ... & Gebru, T. (2019). Model cards for model reporting. Proceedings of the Conference on Fairness, Accountability, and Transparency, 220–229.
16. Dwork, C., Hardt, M., Pitassi, T., Reingold, O., & Zemel, R. (2012). Fairness through awareness. Proceedings of the 3rd Innovations in Theoretical Computer Science Conference, 214–226.
17. Athey, S. (2017). Beyond prediction: Using big data for policy problems. Science, 355(6324), 483–485.
18. Toulis, P., & Kao, E. (2013). Estimation of causal peer influence effects. Proceedings of the 30th International Conference on Machine Learning, 1487–1495.
19. Hernán, M. A., & Robins, J. M. (2020). Causal inference: What if. Chapman & Hall/CRC.
20. Wager, S., & Athey, S. (2018). Estimation and inference of heterogeneous treatment effects using random forests. Journal of the American Statistical Association, 113(523), 1228–1242.
Downloads
Published
Issue
Section
License
Copyright (c) 2023 Journal of Advanced Artificial Intelligence Research
This work is licensed under a Creative Commons Attribution 4.0 International License.
This article is published under the Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
