Evolution of Retailers'Competitive Performance Considering Consumer Network Characteristics
This paper explores a computational experimental model that incorporates a Q-learning algorithm for a network of competing multi-agent retailer-consumer interactions.In the network model,retailers containing different combinations of pricing and service levels are constructed to compete for groups of consumers under different network characteristics(consumer neighbor nodes,consumer network reconnection probability).All retailer agents adjust their product prices and service levels under the Q-learning mechanism to maximize expected sales and profits.Based on our results,we find that:(1)Enhanced consumer interactions are conducive to retailer performance enhancement;(2)The optimal mix is determined by different scenarios.The purpose of this paper is to provide recommendations for retailers competing in complex market environments to select appropriate mix strategies.
万方数据
维普
