Optimizing Vegetable Commodity Pricing and Replenishment: An Integration of ARIMA and Nonlinear Programming Approaches

Abstract

Automated pricing and replenishment decision-making for vegetable items in supermarkets has attracted the attention of many operators and become a trend, and has become an indispensable part of supermarkets for many operators. In order to develop reliable automatic pricing and replenishment decisions for vegetable products, this paper firstly uses logistic regression analysis to obtain the regression equations of total sales and cost-plus pricing for each vegetable category, and then uses the ARIMA time-series forecasting model to forecast the average wholesale prices of vegetable categories for the next 7 days. After selecting the average wholesale price and pricing-sales volume model for each vegetable category, a nonlinear programming model is constructed to solve the total daily replenishment and pricing strategy for each vegetable category in the coming week. Considering the constraints of limited merchandising categories, this paper introduces three constraints: the number of saleable items, the minimum display volume and the selling space, and estimates the future wholesale price by using the historical average to make a prediction. The optimal replenishment quantity and price are derived by combining the nonlinear programming model and guided by the constraint function.