Research On Commodity Pricing and Replenishment Based on Optimization and Forecasting Algorithm

Abstract

With the rapid development of China's commodity economy and people's growing demand for a better life, people's demand for high-quality vegetable products is gradually in-creasing, so Commodity hypermarket needs to ensure that the market's demand for richness and supply of various vegetables is met with a low loss rate. In this paper, the total replenishment amount and pricing strategy of Commodity hypermarket are analyzed and solved based on GWO-BiLSTM algorithm, aiming at providing more effective replenishment and pricing strategies for Commodity hypermarket industry to meet market demand and maximize economic benefits. The value of Pearson correlation coefficient is used to intuitively understand the correlation between sales volume and other factors, and cosine similarity is selected as the clustering method by cluster analysis, which performs well on high-dimensional data sets. The results obtained by the bidirectional long-term and short-term memory network method based on grey wolf optimization have the characteristics of high efficiency and stable output, which can effectively improve the yield. In addition, this paper also discusses the internal relationship and interaction mechanism between the total replenishment amount and pricing strategy of Commodity hypermarket, and further deepens the understanding of the importance of these two factors in the operation of Commodity hypermarket. The research conclusion has guiding significance for Commodity hypermarket to formulate a reasonable replenishment plan and pricing strategy, and is helpful to improve Commodity hypermarket's performance, meet customer needs and achieve sustainable development. At the same time, the research method of this paper can also provide reference for other retail industries.