Lathia et al. [48] also carried out a study of several similarity measures where they concluded that, in the general case, the prediction accuracy of a RS was not affected by the choice of the similarity measure. As a matter of fact and in the context of their work, using a random similarity measure sometimes yielded better results than using any of the well-known approaches.
This implies that the design of a recommender system should first emphasize the analysis of the available sources of knowledge, and then decide about the algorithm accordingly.
RSs that aggregate multiple types of user feedbacks and preferences to build more reliable recommendations.上次给@wentrue 提豆瓣首页的推荐问题时,我后来也想到了这个解决办法,当然aggregate的计算量估计不小。
Development of recommender systems is a multi-disciplinary effort which involves experts from various fields such as Artificial intelligence, Human Computer Interaction, Information Technology, Data Mining, Statistics, Adaptive User Interfaces, Decision Support Systems, Marketing, or Consumer Behavior.
郑大清新 (We just want to work!)
2015-07-30 23:55:33
Roc
2013-05-21 10:28:25
dhcn (Doer)
2012-09-11 09:25:27
dhcn (Doer)
2012-05-24 16:22:50
dhcn (Doer)
2012-05-16 15:10:14
dhcn (Doer)
2012-05-14 16:33:07
dhcn (Doer)
2012-04-29 16:01:32