Exploiting Semantic Product Descriptions for Recommender Systems
msra(2004)
摘要
Content-driven and hybrid recommender systems propose productstocustomersmakinguseofdescriptivefeaturesand behavioral patterns, likewise. While most approaches ex- ploit classical information retrieval techniques, e.g., nearest- neighbor queries in metric spaces, availability and usage of richer semantic meta-information about products may fur- ther improve recommendation quality significantly. Massive taxonomies for product classification are coming of age, e.g, the United Nations Standard Products and Services Classi- fication (UNSPSC), as well as proprietary standards, such as Amazon.com's classification taxonomies for books, DVDs, CDs, and apparel. We exploit suchlike semantic background knowledge in order to leverage powerful inference oppor- tunities for making user profiles, based upon the products these latter customers purchased, more meaningful. Am- ple empirical analysis, both offline and online, demonstrates our proposal's superiority over common existing approaches when user information becomes sparse and implicit ratings prevail.
更多查看译文
关键词
personalization,recommender systems,machine learning,taxonomy,user profiling,metric space,information retrieval,recommender system
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络