A study on vegetable replenishment and pricing based on binomial function and deep learning models

Abstract

Perishable vegetable commodities for supermarkets, the development of its sales strategy is critical. The purpose of this paper is to develop an integrated model to optimize the daily replenishment and pricing strategy of vegetables, so as to improve the operational efficiency and profitability of supermarkets. By analyzing historical sales data, this paper reveals the negative correlation between vegetable sales volume and cost-plus price, and uses various mathematical models to fit the analysis. It is found that the binomial function model with a weekly period can most accurately describe the relationship between sales volume and price. This paper further utilizes the LSTM long- and short- term memory model for the sliding prediction of replenishment volume and combines it with the ARIMA model to predict wholesale prices. Based on the prediction results, this paper establishes an optimization model with profit maximization as the objective and performs parameter optimization by simulated annealing algorithm. The results of the study show that the maximum profit of￥9,708.282 can be achieved by using the strategy proposed in this paper in the study of the situation during the week of July 1 to 7, 2023 This study provides a scientific decision-making tool for superstores, which helps to maximize profits while ensuring the freshness of goods.