Rebalancing and Clearance Pricing of Near-Expiry Inventory in Online Grocery Retail

Ziyuan Zhou, LONG HE, Zhengling Qi, Guangrui Ma, Yuanbo Peng, Yushu Yao, Zhongyi Zha, Mingyong Zhao, Zhenyu Zhuo

Keywords: Inventory rebalancing, dynamic pricing, ML–OR integration, online grocery, perishable inventory, food waste

Abstract: Perishable inventory management remains a critical challenge for online grocery retailers, where mismatches between demand and shelf life can lead to substantial financial losses and food waste. This article describes the development and deployment of an integrated, data-driven system for managing near-expiry (“red-line”) inventory across a nationwide network of micro-fulfillment centers (MFCs) operated by Meituan’s Little Elephant Supermarket. The system jointly optimizes nighttime inventory rebalancing and daytime clearance pricing using a closed-loop learning-and-optimization framework. It combines causal machine learning to estimate price elasticities, a linearized mixed-integer model for inventory rebalancing, and a Markov decision process for dynamic pricing. Since its rollout, the solution has reduced spoilage rates by 20\%, increased revenue from red-line inventory by 14\%, and improved annual profit by approximately 50 million CNY ($\sim$ 7 million USD) as well as saved approximately 18 million CNY ($\sim$ 2.5 million USD) in food waste, as measured across the entire operational network. Our work illustrates how aligning OR insights with adaptive ML tools can deliver scalable, interpretable, and uncertainty-aware decision systems, generating both economic and sustainability gains in complex retail operations.

Submission Number: 86