Automatic Pricing and Replenishment Strategy for Vegetables Based on Multivariate Nonlinear Modeling

Pricing strategy for vegetables occupies an extremely important position in business operations. Since vegetable commodities are time-sensitive, perishable, and price-sensitive, a reasonable pricing strategy can increase supermarket sales and customer satisfaction, as well as increase profits. Pricing needs to take into account not only the cost of the commodity but also market demand, competitive situation, consumer psychology, and other factors. In addition, the pricing strategy should be adjusted according to different seasons, geographic locations, and customer groups in order to maintain a competitive advantage. In conclusion, the pricing strategy of fresh food supermarkets needs to be scientific and flexible in order to adapt to the changing market environment. In this paper, firstly, the improved inverse proportion function is used to describe the relationship between the total sales volume of each vegetable category and cost-plus pricing, and the RMSE of the model for each category is obtained in the range of 0.25-0.5 after fitting the data, which indicates that the predicted value is very close to the real value, and the model fitting effect is better; and then, the time series analysis of the sales volume and the cost of each vegetable category is performed, and the time series analysis is based on the ARIMA model to complete the July 1–7, 2023 data forecast. In order to formulate the daily replenishment quantity and pricing strategy of each category of vegetables for July 1–7, 2023, the multivariate nonlinear constraint model was constructed based on the above model of the relationship between sales volume and cost plus pricing as well as the predicted data of sales volume and cost, and based on the discount factor and discount time point, and the model was solved through the Scipy library.