Research on Pricing and Replenishment Decision Making Based on ARIMA Time Series and Apriori Algorithm

This study addresses the sales and pricing issues of vegetable items in fresh produce superstores. Evaluation and analysis are conducted for six categories of vegetable merchandise to reveal the correlation between the popular single products in each category and the vegetable category through the gray correlation method and Pearson correlation analysis method. In terms of formulating the total daily replenishment and pricing strategy for the coming week that maximizes the profit of the superstore, an ARIMA time-series model is established, combined with the Apriori algorithm and data visualization methods, to formulate a pricing strategy that meets the actual situation. For the replenishment plan of individual products, through the analysis of the sales data of the past three years, the top thirty-three selling individual products are selected as the sellable varieties, and the seasonal decomposition is used to predict the data of each individual product and formulate the replenishment and pricing strategies. Finally, data factors such as temperature impact and consumer demand are combined to provide reference for superstores to plan better replenishment and pricing strategies. Based on actual data and mathematical modeling, this study provides feasible suggestions for superstores to improve revenue and reduce wastage rate, which promotes superstores' operational efficiency and market competitiveness.