Estimating importance of implicit factors in e-commerce recommender systems

In this paper, we discuss the importance of different types of implicit user feedback for creating useful recommendations on an e-commerce website. Each website user may provide us with many different types of implicit feedback and it is difficult to decide which one to use for recommendations. If our recommendation algorithm support using more implicit factors, we should also consider importance and "added value" of each factor. We have identified several widely used implicit factors and conducted real user online testing in order to compare their usefulness for recommending algorithms. We have also proposed some combinations of implicit factors and a test, to see if they improve recommendation performance in comparison with the single factor ones.

[1]  Izak Benbasat,et al.  E-Commerce Product Recommendation Agents: Use, Characteristics, and Impact , 2007, MIS Q..

[2]  Peter Vojtás,et al.  Combining Various Methods of Automated User Decision and Preferences Modelling , 2009, MDAI.

[3]  Sandip Sen,et al.  A Movie Recommendation System – An Application of Voting Theory in User Modeling , 2003, User Modeling and User-Adapted Interaction.

[4]  Yifan Hu,et al.  Collaborative Filtering for Implicit Feedback Datasets , 2008, 2008 Eighth IEEE International Conference on Data Mining.

[5]  Shlomo Berkovsky,et al.  Recipe recommendation: accuracy and reasoning , 2011, UMAP'11.

[6]  Kenta Oku,et al.  A Recommendation System Considering Users' Past / Current / Future Contexts , 2010 .

[7]  John Riedl,et al.  RecBench , 2011, Proc. VLDB Endow..

[8]  Ryen W. White,et al.  Comparing Explicit and Implicit Feedback Techniques for Web Retrieval: TREC-10 Interactive Track Report , 2001, TREC.

[9]  Peter Vojtás,et al.  Pref Shop A Web Shop with User Preference Search Capabilities , 2010, 2010 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology.

[10]  Martin Szomszor,et al.  Comparison of implicit and explicit feedback from an online music recommendation service , 2010, HetRec '10.

[11]  Peter Vojtás,et al.  UPComp - A PHP Component for Recommendation Based on User Behaviour , 2011, 2011 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology.

[12]  Filip Radlinski,et al.  Evaluating the accuracy of implicit feedback from clicks and query reformulations in Web search , 2007, TOIS.

[13]  Peter Vojtás,et al.  How to Learn Fuzzy User Preferences with Variable Objectives , 2009, IFSA/EUSFLAT Conf..

[14]  Mark Claypool,et al.  Implicit interest indicators , 2001, IUI '01.

[15]  Robin D. Burke,et al.  Hybrid Recommender Systems: Survey and Experiments , 2002, User Modeling and User-Adapted Interaction.