Research on Automatic Pricing and Restocking Decisions for Vegetable Products: A Case Study of a Supermarket

For fresh supermarkets, it is crucial to formulate restocking decisions and pricing strategies that maximize profits while meeting market demand. This paper mainly studies the automatic pricing and restocking decisions for vegetable products. Through model assumptions, correlation analysis, and time series methods, the study investigates these decisions. Based on the obtained sales data, Pearson correlation coefficients are calculated to analyze the relationships between different categories and individual product sales. A Long Short-Term Memory (LSTM) time series model is built to forecast future costs, with the model parameters estimated using the least squares method. The optimal restocking and pricing strategies are derived using Random Forest and Autoregressive Integrated Moving Average (ARIMA) models. Additionally, the restocking and pricing problems are treated as a combinatorial optimization problem and solved using a mixed-integer linear programming model to maximize revenue. This paper emphasizes the importance of comprehensive data collection in automatic pricing and restocking decisions to address challenges in the industry.