Modeling Retail Transaction Data for Personalized Shopping Recommendation.
CIKM '14: 2014 ACM Conference on Information and Knowledge Management Shanghai China November, 2014(2014)
摘要
Retail transaction data conveys rich preference information on brands and goods from customers. How to mine the transaction data to provide personalized recommendation to customers becomes a critical task for retailers. Previous recommendation methods either focus on the user-product matrix and ignore the transactions, or only use the partial information of transactions, leading to inferior performance in recommendation. Inspired by association rule mining, we introduce association pattern as a basic unit to capture the correlation between products from both intra- and intertransactions. A Probabilistic model over the Association Patterns (PAP for short) is then employed to learn the potential shopping interests and also to provide personalized recommendations. Experimental results on two real world retail data sets show that our proposed method can outperform the state-of-the-art recommendation methods.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络