An Integrated Deep Learning and Reinforcement Learning Framework for Profit Maximization in Perishable Food Supply Chains

DOI

10.2991/978-94-6463-978-0_15How to use a DOI?

Keywords

Supply Chain Management; Perishable Goods; Demand Forecasting; Deep Learning; Reinforcement Learning; Dynamic Pricing

Abstract

The current study deals with the perishable food supply chain management system with a novel hierarchical AI system that combines the use of the Transformer-based demand forecasting and Proximal Policy Optimization (PPO) reinforcement learning. The predictive engine creates probabilistic store-SKU-day manpower and the prescriptive engine continuously self-determines the replenishment and dynamic markdown pricing. Our framework, parameterized with data of the actual case studies and tested through high-fidelity simulations, results in 184 percent increase in profit in comparison to traditional (s,S) policies, 70 percent lowering of the waste in comparison with standalone forecasting, and 82 percent of waste reduction in comparison with traditional (s,S) policies. Field validation shows 18% better profits and 32% decreases in wastage during actual operations, and proved strong during the pandemic-like growth and decline in demand and supply.

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  - S. Satyanarayana
AU  - Srinubabu Kilaru
AU  - Kommuri Venkatrao
PY  - 2025
DA  - 2025/12/31
TI  - An Integrated Deep Learning and Reinforcement Learning Framework for Profit Maximization in Perishable Food Supply Chains
BT  - Proceedings of the 1st Engineering Data Analytics and Management Conference (EAMCON 2025)
PB  - Atlantis Press
SP  - 156
EP  - 171
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-978-0_15
DO  - 10.2991/978-94-6463-978-0_15
ID  - Satyanarayana2025
ER  -