Lag-Aware Causal Multimodal Transformer for Supply Chain Demand Forecasting
DOI:
https://doi.org/10.66238/smsrj.v4i2.78Keywords:
demand forecasting, multimodal transformer, lag alignment, predictive causality, supply chain, time seriesAbstract
Demand forecasting increasingly relies on heterogeneous signals, but multimodal fusion is often temporally naive: exogenous channels are aligned by timestamp even when their effect on demand is delayed. This paper introduces a Lag-Aware Causal Multimodal Transformer (LACMT) that separates representation learning from train-only predictive-causality screening. The model first estimates channel-specific delay candidates by correlating each lagged exogenous channel with residual demand after autoregressive adjustment. These lag estimates are then converted into horizon-aligned causal context tokens and fused with a compact multimodal Transformer through a horizon-conditioned prediction head. To avoid unsupported causal claims, the screening stage is interpreted as Granger-style predictive causality rather than intervention-level identification. A controlled supply-chain benchmark with known lag structure is used so that both forecast accuracy and lag recovery can be audited. Across two neural random seeds, LACMT attains 7-day RMSE 8.630±0.101, MAE 6.634±0.093, and sMAPE 24.324±0.572. The unconstrained multimodal Transformer records the lowest 7-day RMSE (8.240±0.239), while LACMT improves 7-day RMSE by 5.7% and sMAPE by 24.1% over a linear lag-aware Ridge baseline and recovers four of five planted influential lags exactly. These results show that explicit lag alignment adds interpretable temporal structure and competitive long-horizon performance without conflating predictive causality with structural causation.
References
1. Y. Wang, G. Ding, Z. Zeng, and S. Yang, “Causal-Aware Multimodal Transformer for Supply Chain Demand Forecasting: Integrating Text, Time Series, and Satellite Imagery,” IEEE Access, vol. 13, pp. 176813–176829, 2025, doi: 10.1109/ACCESS.2025.3619552.
2. A. Vaswani et al., “Attention Is All You Need,” in Advances in Neural Information Processing Systems 30, 2017, pp. 5998–6008.
3. B. Lim, S. Ö. Arık, N. Loeff, and T. Pfister, “Temporal Fusion Transformers for interpretable multi-horizon time series forecasting,” International Journal of Forecasting, vol. 37, no. 4, pp. 1748–1764, 2021, doi: 10.1016/j.ijforecast.2021.03.012.
4. H. Zhou et al., “Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting,” Proc. AAAI Conf. Artif. Intell., vol. 35, no. 12, pp. 11106–11115, 2021, doi: 10.1609/aaai.v35i12.17325.
5. T. Zhou, Z. Ma, Q. Wen, X. Wang, L. Sun, and R. Jin, “FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting,” in Proc. ICML, PMLR 162, 2022, pp. 27268–27286.
6. Y. Nie, N. H. Nguyen, P. Sinthong, and J. Kalagnanam, “A Time Series Is Worth 64 Words: Long-term Forecasting with Transformers,” in Proc. ICLR, 2023.
7. B. N. Oreshkin, D. Carpov, N. Chapados, and Y. Bengio, “N-BEATS: Neural basis expansion analysis for interpretable time series forecasting,” in Proc. ICLR, 2020.
8. D. Salinas, V. Flunkert, J. Gasthaus, and T. Januschowski, “DeepAR: Probabilistic forecasting with autoregressive recurrent networks,” International Journal of Forecasting, vol. 36, no. 3, pp. 1181–1191, 2020, doi: 10.1016/j.ijforecast.2019.07.001.
9. S. S. Rangapuram, M. W. Seeger, J. Gasthaus, L. Stella, Y. Wang, and T. Januschowski, “Deep State Space Models for Time Series Forecasting,” in Advances in Neural Information Processing Systems 31, 2018.
10. S. Hochreiter and J. Schmidhuber, “Long Short-Term Memory,” Neural Computation, vol. 9, no. 8, pp. 1735–1780, 1997, doi: 10.1162/neco.1997.9.8.1735.
11. K. Cho et al., “Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation,” in Proc. EMNLP, 2014, pp. 1724–1734, doi: 10.3115/v1/D14-1179.
12. T. Baltrušaitis, C. Ahuja, and L.-P. Morency, “Multimodal Machine Learning: A Survey and Taxonomy,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 41, no. 2, pp. 423–443, 2019, doi: 10.1109/TPAMI.2018.2798607.
13. Y.-H. H. Tsai, S. Bai, P. P. Liang, J. Z. Kolter, L.-P. Morency, and R. Salakhutdinov, “Multimodal Transformer for Unaligned Multimodal Language Sequences,” in Proc. ACL, 2019, pp. 6558–6569, doi: 10.18653/v1/P19-1656.
14. C. W. J. Granger, “Investigating Causal Relations by Econometric Models and Cross-spectral Methods,” Econometrica, vol. 37, no. 3, pp. 424–438, 1969, doi: 10.2307/1912791.
15. X. Zheng, B. Aragam, P. K. Ravikumar, and E. P. Xing, “DAGs with NO TEARS: Continuous Optimization for Structure Learning,” in Advances in Neural Information Processing Systems 31, 2018.
16. J. Runge, P. Nowack, M. Kretschmer, S. Flaxman, and D. Sejdinovic, “Detecting and quantifying causal associations in large nonlinear time series datasets,” Science Advances, vol. 5, no. 11, eaau4996, 2019, doi: 10.1126/sciadv.aau4996.
17. J. Pearl, Causality: Models, Reasoning, and Inference, 2nd ed. Cambridge, U.K.: Cambridge University Press, 2009.
18. Chen, T., Shang, W., & Guo, Z. (2024). Xsla: An SLA-aware heterogeneous XPU scheduling framework for edge AI inference. World Journal of Information Technology, 2(2), 48–59.
19. Zou, J., Qin, Y., & Rhee, M. (2024). Beyond model scale: A task-aware reliability benchmark for large language models in clinical decision support. Innovation and Technology Studies, 1(1), 39–47.
20. Fang, Q. (2024). Bias-aware large language models for equitable educational feedback and assessment. Trends in Social Sciences and Humanities Research.
21. Qin, Y., Zou, J., & Rhee, M. (2022). An AI-driven intelligent transaction execution framework for internet finance platforms: Cost-sensitive real-time integrity interdiction. Eurasia Journal of Science and Technology, 4(2), 36–44.
22. Wang, Y., & Zhang, C. (2023). AERIS: Adaptive executor scoped resource management for privacy preserving data processing in Apache Spark. Eurasia Journal of Science and Technology, 5(2), 25-33.
23. Zhao, W., & Wang, B. (2022). CAPA: A prediction‑driven autoscaling framework for SLO‑aware cloud‑native machine learning inference. Journal of Computer Science and Electrical Engineering, 4(1), 8-16.
24. Guo, Z., Chen, T., & Shang, W. (2022). Class‑conditional intermediate‑domain adversarial adaptation for cross‑device acoustic scene classification. Journal of Computer Science and Electrical Engineering, 4(1), 26-35
25. Shen, A., & Huang, S. (2022). A systems-aware framework for intelligent large-scale recommendation models. Journal of Computer Science and Electrical Engineering.
26. Fang, Q. (2024). TRUE-EWS: Trustworthy early warning with equalized conformal guarantees for equitable student support in U.S. education. Educational Research and Human Development.
27. Shen, A. (2023). Compute-efficient scaling of large sequential recommendation models under dynamic user behavior. World Journal of Information Technology.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Ethan Vale, Maya Chen
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
All articles in the Social and Management Sciences Research Journal are published under the Creative Commons Attribution 4.0 (CC BY 4.0) license. Users can share, copy, distribute, and adapt the work, including for commercial purposes, provided proper attribution is given to the authors and the journal.
