Automatic Pricing and Replenishment Decisions for Vegetable Products

The perishable nature of vegetable products poses significant challenges in inventory management and pricing, often leading to high waste rates and economic losses. This study addresses these issues by proposing an automated pricing and replenishment decision model that leverages statistical analysis, regression methods, and time-series forecasting. Utilizing three years of sales data from a supermarket, the research develops models to analyze the relationship between sales volume and cost-plus pricing, optimize replenishment strategies, and predict pricing for various vegetable categories. The results demonstrate that dynamic pricing and replenishment decisions can reduce waste, increase profits, and enhance supply chain efficiency. The study highlights the practicality of using machine learning models like LSTM to forecast demand and pricing while acknowledging limitations such as simplifying assumptions and the need for multidimensional data. Future research directions include integrating external factors, such as climate impacts, to improve the models adaptability and accuracy.