Research of Agent collaborative filtering model based on user's feedback
Xiaowei Li · Caai Transactions on Intelligent Systems · 2007
In order to serve users with more accurate information,the Agent collaborative filtering model—ACFM based on users' feedback and the dynamic Q learning algorithm are put forward,and users' interesting model is built.ACFM uses the method of users' interesting feedback consisted of implicit feedback and interactive feedback to realize collaborative filtering.Experimental results show that compared with traditional search engine,ACFM is more effective in predicting users' interests,and has more recalls and precision degree in recommending information when inputting the same inquire words.