Automated Pricing and Replenishment Decision for Vegetable Commodities Based on ARIMA Modeling and Linear Regression Model

Vegetable commodities are not easy to keep for a long time, and in order to meet consumer demand and cope with market changes, fresh food superstores need to replenish vegetable commodities. This paper focuses on the replenishment and pricing decision of vegetable commodities and establishes Pearson correlation analysis model, K-means clustering model, time series model, and linear programming model to solve the problem. First, analyze the distribution law of different categories of different single-item vegetable sales, introduce the Pearson correlation analysis model to analyze the correlation between each category, and use the K-means clustering model to analyze the relationship between the sales volume of each single item. Then, the formula for the replenishment volume is determined, the ARIMA time series model is used to predict the sales volume of each category in the coming week, and the linear regression model is used to determine the optimal markup rate as well as the maximum revenue of each category in the coming week. The proposed model is suitable for handling large amounts of data with high accuracy and flexibility.