Vegetable category replenishment and pricing decision model in fresh food supermarkets

Abstract

The vegetable commodities in fresh food supermarkets generally have the characteristics of a wide variety of categories, different origins, and a short shelf life. Moreover, the product quality continuously deteriorates as the sales time increases, and the corresponding price continuously decreases as the sales time increases. At the same time, the purchase and trading time of vegetables is usually from 3:00 to 4:00 in the morning, and the daily sales volume of dishes is unknown. Therefore, merchants must make replenishment decisions for various vegetable categories on the same day without exactly knowing the pricing and purchase quantity of specific dishes. Thus, reliable market demand analysis is particularly important for replenishment and pricing decisions. Based on the historical sales data of six vegetable categories distributed by a supermarket, this paper first uses the Auto Regressive Integrated Moving Average (ARIMA) model to predict the replenishment quantity of each category in the next seven days. Then, through the Back Propagation (in neural networks) (BP), it fits the relationship between sales volume, cost-plus rate, and wholesale price. Combined with the “cost-plus pricing” method, it predicts the pricing of each category of dishes in the next seven days, providing a certain reference for the replenishment and pricing decisions of supermarkets.