LSI 기법을 이용한 전자상거래 추천자 시스템의 시뮬레이션 분석 = Simulation Study on E-commerce Recommender System by Use of LSI Method

다국어 초록 (Multilingual Abstract)

A recommender system for E-commerce site receives information from customers about which products they are interested in, and recommends products that are likely to fit their needs. In this paper, we investigate several methods for large-scale product purchase data for the purpose of producing useful recommendations to customers. We apply the traditional data mining techniques of cluster analysis and collaborative filtering(CF), and CF with reduction of product-dimensionality by use of latent semantic indexing(LSI). If reduced product-dimensionality obtained from LSI shows a similar latent trend of customers for buying products to that based on original customer-product purchase data, we expect less computational effort for obtaining the nearest-neighbor for target customer may improve the efficiency of recommendation performance. From simulation experiments on synthetic customer-product purchase data, CF-based method with reduction of product-dimensionality presents a better performance than the traditional CF methods with respect to the recall, precision and F1 measure. In general, the recommendation quality increases as the size of the neighborhood increases. However, our simulation results shows that, after a certain point, the improvement gain diminish. Also we find, as a number of products of recommendation increases, the precision becomes worse, but the improvement gain of recall is relatively small after a certain point. We consider these informations may be useful in applying recommender system.

참고문헌 (Reference)

1 "Using Linear Algebra for Intelligent Information Retrieval" 37 : 573-595, 1995

2 "Social Information Filtering: Algorithm for Automating Word of Mouth" 210-217, 1995

3 "Recommending and Evaluating Choices in a Virtual Community of Use" 194-201, 1999

4 "Recommender Systems in E-Commerce" 1999

5 "Recommender Systems in E-Commerce" 1999

6 "Recommender Systems" 40 (40): 1997

7 "Learning Collaborative Information Filters" 1998

8 "Indexing by Latent Semantic Analysis" no. 6 : 391-407, 1990

9 "GroupLens: Applying Collaborative Filtering to Usenet News" 40 (40): 77-87, 1997

10 "Fast Algorithms for Association Rules" 487-499, 1994

11 "Empirical Analysis of Predictive Algorithms for Collaborative Filtering" 43-52, 1998

12 "Combining Social Networks and Collaborative Filtering" 40 (40): 63-65, 1997

13 "Combining Collaborative Filtering with Personal Agents for Better Recommendations" 439-446, 1999

14 "Analysis of Recommendation Algorithm for E-Commerce" 2000

15 "An Algorithm Framework for Performing Collaborative Filtering" 1999