Agent-based merchandise management in Business-to-Business Electronic Commerce

Abstract

Currently, there is cutthroat competition in the retail industry, and retail companies struggle for survival. Merchandise management—selecting desirable merchandise, disposing of slow-selling goods and ordering and distributing them—is important to a retailer's success because merchandise is the basis of retailing. Particularly because in an Electronic Commerce (EC) environment, customer preferences are very diverse and their merchant loyalty level is very low, companies should acknowledge the changes in customer demand patterns quickly and respond to them appropriately. However, until now, most retailers have depended on humans for merchandise management. Because there are too many merchandise and brands, it is impossible for merchandise managers to evaluate, compare, select and dispose of merchandise effectively. Retailers need a system that can perform merchandise managers' jobs autonomously, continuously and efficiently. In this paper, we propose an agent-based system for merchandise management, which performs evaluating and selecting merchandise and predicting seasons and building purchase schedules autonomously in place of human merchandise managers under a Business-to-Business (B2B) EC environment. In order to facilitate the agent's intelligent behavior, several analysis tools such as Data Envelopment Analysis (DEA), Genetic Algorithm (GA), Linear Regression and Rule Induction Algorithm are incorporated into the system. Lastly, the proposed system is verified in its application to a duty-free shop. The proposed system would accomplish merchandise management timely, autonomously and efficiently, and the effective merchandise management would reduce the inventory level while increasing sales and profits. The agent-based merchandise management system will enhance a retail company's potential for success. Moreover, it will be necessary for survival in the B2B EC.