EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Lag-Aware Causal Multimodal Transformer for Supply Chain Demand Forecasting

Ethan Vale, Maya Chen

SOCIAL AND MANAGEMENT SCIENCES RESEARCH JOURNAL · 17.09.2026 · 4 (2) · 178-189

DOI: 10.66238/smsrj.v4i2.78 ↗

Kurz gefasst

Fachartikel in der Zeitschrift SOCIAL AND MANAGEMENT SCIENCES RESEARCH JOURNAL, online erschienen am 17.09.2026. Verfasst von Ethan Vale und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Zitieren

APA

Vale, E., & Chen, M. (2026). Lag-Aware Causal Multimodal Transformer for Supply Chain Demand Forecasting. SOCIAL AND MANAGEMENT SCIENCES RESEARCH JOURNAL, 4(2), 178-189. https://doi.org/10.66238/smsrj.v4i2.78

Vancouver

Vale E, Chen M. Lag-Aware Causal Multimodal Transformer for Supply Chain Demand Forecasting. SOCIAL AND MANAGEMENT SCIENCES RESEARCH JOURNAL. 2026;4(2):178-189. doi:10.66238/smsrj.v4i2.78

BibTeX
@article{Vale2026,
  author = {Vale, Ethan and Chen, Maya},
  title = {Lag-Aware Causal Multimodal Transformer for Supply Chain Demand Forecasting},
  journal = {SOCIAL AND MANAGEMENT SCIENCES RESEARCH JOURNAL},
  year = {2026},
  volume = {4},
  number = {2},
  pages = {178--189},
  doi = {10.66238/smsrj.v4i2.78}
}
Kostenlos starten →