基于混合用戶模型的協(xié)同過濾推薦算法研究

1、重慶大學(xué)碩士學(xué)位論文基于混合用戶模型的協(xié)同過濾推薦算法研究姓名：袁先虎申請學(xué)位級別：碩士專業(yè)：計算機(jī)軟件與理論指導(dǎo)教師：王茜2010-04重慶大學(xué)碩士學(xué)位論文 英文摘要 II ABSTRACT Widely using of Internet and rapidly development of E- commerce caused information overload, which made difficulties f

2、or consumers to find their needed products within a mass of product information, thus E- commerce recommender systems emerge as the times require. Today, E- commerce recommender systems are immat

3、ure in practical use, and still have a lot of problems, like the quality of recommendation being seriously depressed by enormous and sparse ratings of consumers, bad system expansibility, bad recommendat

4、ion real- time, etc. To solve these main problems of current recommender systems, this dissertation valuably explores and researches the key techniques of user model and collaborative filtering algorith

5、ms in E- commerce personalized recommender systems. Collaborative filtering is the most widely used and successful technology for personalized recommender systems. However it faces challenges of scala

6、bility and recommendation accuracy. Collaborative filtering can be divided into memory based and model based. The former is more accurate while the latter performs better in scalability. This pap

7、er proposes a hybrid user model. The recommender system based on this model not only holds the advantage of recommendation accuracy in memory- based method, but also has the scalability as goo

8、d as model- based method. In the aspect of user model, the dissertation analyses defects of classical user model of collaborative filtering recommendation. And hybrid user model is constructed ba

9、sed on item content descriptions and demographic information. The hybrid user model condenses item content description, demographic information and user- item rating matrix, which raises the densit

10、y of data and helps to solve the problems of data sparsity and hard rating obtainment. Feature interest measure is introduced in the hybrid user model, which can reflect the degree of featur

11、e preference of users and obtain more accurate similarity between target user and the neighbors. In the aspect of collaborative filtering, this dissertation analyses sparsity, scalability, real- ti

12、me and recommendation accuracy issues of collaborative filtering algorithms in current E- commerce personalized recommender systems. To solve these problems, collaborative filtering recommendation algori