Intelligent User Preference Mining

Abstract

A business-to-consumer environment can be developed through software agents (Guan, Zhu, & Maung, 2004; Maes, 1994; Nwana & Ndumu, 1996; Wang, Guan, & Chan, 2002) to satisfy the needs of consumers patronizing online e-commerce or m-commerce stores. This includes intelligent filtering services (Chanan & Yadav, 2000) and product brokering services to understand user’s needs better before alerting users of suitable products according to their preference. We present an approach to capture individual user response towards product attributes including nonquantifiable responses. The proposed solution can capture the user’s specific preference and recommend a list of products from the product database. With the proposed approach, the system can handle any unaccounted attribute that is undefined in the system. The system is able to cater to any unaccounted attribute through a general descriptions field found in most product databases. In addition, the system can adapt to changes in user’s preference.