易腐品智能补货与定价模型

Intelligent Replenishment and Pricing Model for Perishables

摘要: 针对商超中易腐品的保质期短造成难以补货定价的问题，该研究依据易腐品时间–销售量热力图，将其按季节划分，再利用斯皮尔曼相关系数分析影响销售量的因素，总结并构造了收益最大化预测补货定价模型。在模型基础上，使用BP (Back Propagation)神经网络拟合总销量与成本加成定价的函数关系，并使用LSTM (Long Short Term Memory)网络预测未来的销售量和进价。最后，使用粒子群算法寻找最优补货量和定价策略，使商超收益最大化，结果得到了90.39%的提升。该研究为商超制定合理的补货和定价策略提供了有益的指导，有助于提高销售额和利润率。

Abstract: Aiming at the problem that the short shelf life of perishables in stores causes difficulty in replenishment and pricing, this study summarizes and constructs a revenue maximization predictive replenishment pricing model based on the perishables time-sales heat map, which is divided into seasons, and then analyzes the factors affecting the sales volume by using the Spearman’s correlation coefficient. On the basis of the model, a BP (Back Propagation) neural network is used to fit the functional relationship between the total sales volume and the cost-plus pricing, and an LSTM (Long Short Term Memory) network is used to predict the future sales volume and the purchase price. Finally, particle swarm algorithm is used to find the optimal replenishment volume and pricing strategy to maximize the revenue of the superstore, which got 90.39% improvement. This study provides useful guidance for superstores to develop reasonable replenishment and pricing strategies, which can help to increase sales and profitability.