웹 로그 분석을 이용한 추천에이전트의 개발 = Development of Recommendation Agents through Web Log Analysis

다국어 초록 (Multilingual Abstract)

In accordance with increase of internet use, the practical worth of web log files has been getting larger. The analysis of log data recorded in web server can be applied to effectual layout of web pages, interface design, and purchasing patterns of customers, etc., and in on-line electronic commerce, it puts analysis of behavior patterns from users to practical use for products recommendation. In most of electronic commerce sites, the recommendation ways have been made use of statistical analysis or simple process by category-oriented, but these can't represent diverse correlation among products and also hardly reflect users' purchasing patterns precisely. In this thesis, we develop more efficient recommendation agents, which get achieved more suitable recommendation using both sequential patterns and association rules to extract adequate relationship among products in category-independent, and also enhanced the utility of recommendation by providing the degree of relation among diverse patterns with weight concretely.