A Deep Learning-Based Demand Forecasting Method for Retail Supply Chains Using LSTM and Attention Mechanism

DOI

10.2991/978-94-6463-845-5_100How to use a DOI?

Keywords

Demand Forecasting; Retail Supply Chain; LSTM; Attention Mechanism; Deep Learning

Abstract

Demand forecasting is a critical task in retail supply chain management, yet traditional models often fall short in handling nonlinear patterns and diverse data sources. This paper presents a deep learning approach that combines LSTM networks with an attention mechanism to capture both temporal dependencies and contextual signals such as pricing and promotions. Evaluated on real-world retail data, the proposed model outperforms classical methods like ARIMA and XGBoost in terms of accuracy and generalization. It also offers interpretability through attention visualization and performs reliably across various product categories. The results suggest that this method is well-suited for practical forecasting tasks. Future work will explore the integration of external factors and real-time deployment strategies.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, 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 license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Guangren Pan
AU  - Baishan Xue
AU  - Yao Lu
AU  - Xue Li
PY  - 2025
DA  - 2025/09/16
TI  - A Deep Learning-Based Demand Forecasting Method for Retail Supply Chains Using LSTM and Attention Mechanism
BT  - Proceedings of the 2025 6th International Conference on Management Science and Engineering Management (ICMSEM 2025)
PB  - Atlantis Press
SP  - 1026
EP  - 1032
SN  - 2667-1271
UR  - https://doi.org/10.2991/978-94-6463-845-5_100
DO  - 10.2991/978-94-6463-845-5_100
ID  - Pan2025
ER  -