Automated pricing and replenishment strategies for vegetable products based on SVR and simulated annealing

Abstract

In fresh supermarkets, the shelf life of general vegetable products is relatively short, and the quality deteriorates with the increase of sales time, and most varieties cannot be sold the next day if they are not sold on the same day. However, due to the fact that the vegetables sold by fresh supermarkets often have a wide variety and different origins, merchants need to make replenishment decisions for each vegetable category on the same day without accurately judging the specific single product and purchase price, and the reliability of market demand analysis is very important for supermarkets to make correct replenishment and pricing decisions. Based on the relevant data of sales details and wholesale prices of six vegetable commodities operated by a supermarket from 2020 to 2023, this paper uses Fourier series and Gaussian function to predict the sales volume of vegetable single products, clarifies the relationship between supermarket revenue and the pricing and replenishment quantity of vegetable products based on multiple linear regression theory, and establishes a pricing strategy model based on simulated annealing algorithm and SVR. On the premise of trying to meet the market's demand for various categories of vegetable products, the supermarket will make the maximum profit, so as to help the supermarket further formulate the pricing and replenishment plan of a single product.