A Research Of Recommendation Algorithm Based On Cloud Model
With the popularity of Internet and the development of e-commerce, recommendation system is becoming more and more important research content of e-commerce IT technology. The problem is the fuzziness and uncertainty of traditional recommendation system that caused by extremely sparse rating data. The paper use cloud model which are knowledge representation in quality and bridge function of the conversion between quality and quantity, provide an item classification recommendation algorithm based on cloud model. The algorithm takes fully into account the classification of specific items and users different favorable levels to the same rating or not rating item, avoids the shortcoming of treating user totally rating as single vector, and can overcome effectively the affects of extremely sparse user ratings. The experiment result show the performance of item classification recommendation algorithm based on cloud model is better.
cloud model items classification similarity recommendation system
Wu Yueping Zheng Jianguo
School of Computer and Information Shanghai Second Polytechnic University Shanghai China School of Business and Management Donghua University Shanghai China
国际会议
厦门
英文
469-473
2010-10-29（万方平台首次上网日期，不代表论文的发表时间）