Intelligent Pricing and Replenishment Strategy for Vegetables in Supermarkets Based on ARIMA Prediction and Particle Swarm Optimization Algorithm

Today's technological strength is gradually increasing, the process of digital technology is accelerated, automatic pricing and replenishment decisions in the vegetable commodity category can be digitally mined to obtain a reasonable and beneficial strategy for the interests of the superstore. The aim of this problem is to solve the problems of superstore replenishment and pricing by establishing mathematical models, analyzing the existing data, and solving the problems of superstore replenishment and pricing through the strategies of prediction and optimization, so as to reduce the rate of wastage and improve the profitability. Firstly, the distribution pattern and interrelationship of the sales volume of each category as well as single product of vegetables are analyzed by using Spearman's correlation coefficient, line graphs, bar graphs and descriptive statistics realization. Then, the planning function of the superstore's revenue and the total daily replenishment of each vegetable category is established, and the ARIMA model is used to predict the future sales volume, which is solved by combining with the particle swarm algorithm, and the Monte Carlo algorithm is used to corroborate the correctness of the answer. Finally, the constraints are set to satisfy the market needs, solved by particle swarm algorithm to get the maximum amount of profit for the superstore, establish a linear planning function, and continue to solve by particle swarm algorithm to get the daily replenishment plan in the given vegetable item. The proposed algorithm can avoid falling into local optimal solutions and has global optimality.