Research on Supermarket Pricing and Replenishment Strategy Based on LSTM and Grey Correlation Analysis

This study is devoted to solving the problems of replenishment and pricing decisions in the sales of vegetable categories in superstores in order to maximize the revenue of superstores. In response to the market demand analysis, we determined the relational equation between total sales and cost-plus pricing for each vegetable category based on a nonlinear fitted regression model and LSTM time series forecasting, and then derived the pricing strategy for the coming week to ensure the maximal revenue of the superstore. Through the grey prediction model GM (1,1) and linear programming model, we screened 36 optimal replenishment items from 61 individual items, and combined the constraints of individual item pricing relationship, cost relationship, and replenishment utilization rate to derive the individual item replenishment quantity and pricing strategy, aiming to maximize the hypermarket's revenue under the premise of meeting the market demand. Thus, it provides a powerful decision support for hypermarket operation and a valuable reference for research and practice in similar fields.