OTPTO: Joint Product Selection and Inventory Optimization in Fresh E-commerce Front-End Warehouses
Zheming Zhang, Yan Jiang, Qingshan Li, Ai Han
TL;DR
The paper tackles joint product selection and inventory optimization for front-end fresh-e-commerce warehouses to maximize the full order fulfillment rate, formalized as maximizing $r = \frac{1}{T} \sum_{t=1}^T r_t = \frac{1}{T} \sum_{t=1}^T \frac{O_{F,t}}{O_t}$. It introduces OTPTO, a multi-task Optimize-then-Predict-then-Optimize framework that first solves a 0-1 MILP OM1 to obtain historically optimal stocking decisions, then trains two predictors PM1 (binary) and PM2 (regression) using LightGBM, followed by an OM2 post-processing phase to ensure feasibility under capacity constraints. Empirical results on JD.com’s 7Fresh data show OTPTO improves the full order fulfillment rate by 4.34 percentage points (relative 7.05%) and narrows the gap to the optimum by 5.27% compared with PTO, with additional robustness across multiple warehouses. Key contributions include (i) a novel joint optimization-prediction framework that leverages historical optimal decisions, (ii) targeted sampling, labeling, and feature strategies to address label consistency and learning challenges, and (iii) practical insights for front-end inventory management in fresh e-commerce settings.
Abstract
In China's competitive fresh e-commerce market, optimizing operational strategies, especially inventory management in front-end warehouses, is key to enhance customer satisfaction and to gain a competitive edge. Front-end warehouses are placed in residential areas to ensure the timely delivery of fresh goods and are usually in small size. This brings the challenge of deciding which goods to stock and in what quantities, taking into account capacity constraints. To address this issue, traditional predict-then-optimize (PTO) methods that predict sales and then decide on inventory often don't align prediction with inventory goals, as well as fail to prioritize consumer satisfaction. This paper proposes a multi-task Optimize-then-Predict-then-Optimize (OTPTO) approach that jointly optimizes product selection and inventory management, aiming to increase consumer satisfaction by maximizing the full order fulfillment rate. Our method employs a 0-1 mixed integer programming model OM1 to determine historically optimal inventory levels, and then uses a product selection model PM1 and the stocking model PM2 for prediction. The combined results are further refined through a post-processing algorithm OM2. Experimental results from JD.com's 7Fresh platform demonstrate the robustness and significant advantages of our OTPTO method. Compared to the PTO approach, our OTPTO method substantially enhances the full order fulfillment rate by 4.34% (a relative increase of 7.05%) and narrows the gap to the optimal full order fulfillment rate by 5.27%. These findings substantiate the efficacy of the OTPTO method in managing inventory at front-end warehouses of fresh e-commerce platforms and provide valuable insights for future research in this domain.