Research on Vegetable Replenishment and Pricing Strategies for Supermarkets Based on Time Series and Multi-Objective Planning

This paper conducts in-depth research on the replenishment and pricing strategy of vegetable products in fresh food superstores, and comprehensively analyzes the vegetable sales data by using Spearman correlation coefficient test, Support Vector Regression (SVR), Long and Short-term Memory Recurrent Neural Networks (LSTM), Multi-Objective Planning and Particle Swarm Optimization Algorithm, etc. The data are integrated, cleaned, and visualized to reveal the changing law of vegetable category and specific product sales volume. Firstly, through data integration and cleaning and visualization, the changing law of vegetable category and single product sales volume is revealed, and the interrelationship between categories and single products is explored by using Spearman's correlation coefficient test; Secondly, combined with the cost-plus model and the time series prediction, the replenishment volume and pricing strategy of the next 7 days are provided with scientific basis; Finally, considering the actual operational constraints, the specific replenishment volume and pricing strategy are given through multi-objective planning and particle swarm optimization algorithm, a specific replenishment and pricing scheme is given. In addition, this paper also collects data from consumer preference, market competition, natural factors, and other aspects to provide comprehensive suggestions for the optimization strategy of the superstore and evaluates and improves the model.