With the improvement of people's living standards, people's requirements for the freshness and variety richness of food are also constantly increasing. Due to the short shelf life of fresh vegetable products, reasonable prediction and formulation of pricing and replenishment strategies have a significant impact on supermarket revenue. This article first cleans the data and uses Excel and Grabbs statistics to determine the missing and abnormal values of the data. The missing values are supplemented by 0, and the abnormal values are determined and eliminated through manual intervention. Conduct descriptive statistics on the preprocessed data to obtain partial data features of categories classified by day and month. Analyze numerical features to determine the distribution pattern of data using monthly classification, and then use SPSS PRO to conduct Spearman correlation analysis to obtain the relationship between vegetable categories. Next, this article quantifies six data indicators, including daily sales volume of each category, average unit price during normal sales, and discount degree. Then, MATLAB is used for regression fitting analysis to obtain the relationship expressions between each indicator and the total sales volume. Excel analysis is used to summarize the data to obtain the available variety information of each item of vegetables in the supermarket from June 24th to 30th, And use Python software to establish a time series prediction model to analyze and process the information of supermarket products, and obtain the demand for individual products on July 1st. Using the single product selected by the supermarket as the 0-1 decision variable, and the total operating profit and supply demand relationship of the supermarket as the dual objective variables, a multiple linear regression model is constructed to obtain the final replenishment policy and pricing decision. The data in this paper is from the National College Students Mathematical Modeling Competition C question.