상품구조 및 사용자 경향성에 기반한 추천 시스템

• 영문명: Recommender System based on Product Taxonomy and User's Tendency
• 발행기관: 한국산업경영시스템학회
• 저자명: 임헌상(Heonsang Lim) 김용수(Yong Soo Kim)
• 간행물 정보: 『한국산업경영시스템학회 학술대회』2013년 춘계학술대회 논문집, 269~273쪽, 전체 4쪽
• 주제분류: 공학 > 산업공학
• 파일형태: PDF
• 발행일자: 2013.05.11

영문 초록

This article develops a novel and flexible recommender system based on product taxonomy and usage patterns of users. The proposed system consists of the following four steps. First, a product-preference matrix for each user is estimated through a linear combination of the click, basket placement and purchase statuses. Second, we construct the preference matrix of the genre and that of the specific type by computing the ratios of the number of clicks, basket placement and purchases of a product to the totals. Third, the popularity and similarity levels of a user's clicked product are estimated using entropy index. Fourth, a product is recommended to each user using recommendations such as collaborative filtering and content based filtering based on this information. To assess the effectiveness of the proposed approach, an empirical study was conducted by constructing the experimental e-commerce site. It is clearly shown that the proposed hybrid method is superior to conventional methods.

목차

Abstract

1. 서론

2. 전자 상거래 사이트에서 수집한 데이터 형태

3. 개발된 추천 시스템

4. 실험 평가

5. 결론 및 추후 연구 방향

References

키워드

Recommender System Collaborative Filtering Content based Filtering Product Taxonomy