Implicit behavior addition for improving recommendations

Recommender system is used in e-commerce websites. An e-commerce website should capture the customer's preferences at best to recommend her well. The core area around which a recommender system is build is user profiling. Researchers and industry professionals are working in the direction of user profiling to improve the recommendations. This paper is an attempt to closely study the impact of adding implicit behavior of a user in recommendation results generation. It highlights the conceptual overview of some implicit behavior based attributes which are useful in producing quality recommendations through reordering. In Context of Recommender system Top-N occupancy is of high importance. Products getting slot in Top-N occupancy are highly likely to be converted to sales and gain users' trust. Considering this fact, we are proposing an implicit behavior based solution which mainly focuses on Top-N occupancy. It also presents an approach through which similarity in implicit behavior based attribute is calculated.

[1]  Yoav Shoham,et al.  Fab: content-based, collaborative recommendation , 1997, CACM.

[2]  Chen Lin,et al.  Personalized news recommendation via implicit social experts , 2014, Inf. Sci..

[3]  Gediminas Adomavicius,et al.  Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions , 2005, IEEE Transactions on Knowledge and Data Engineering.

[4]  Eunseok Lee,et al.  A User Modeling Using Implicit Feedback for Effective Recommender System , 2008, 2008 International Conference on Convergence and Hybrid Information Technology.

[5]  Vimala Balakrishnan,et al.  Implicit user behaviours to improve post-retrieval document relevancy , 2014, Comput. Hum. Behav..

[6]  Yasufumi Takama,et al.  Proposal of user modeling method and recommender system based on personal values , 2012, The 6th International Conference on Soft Computing and Intelligent Systems, and The 13th International Symposium on Advanced Intelligence Systems.

[7]  Yue Xu,et al.  Acquiring User Information Needs for Recommender Systems , 2013, 2013 IEEE/WIC/ACM International Joint Conferences on Web Intelligence (WI) and Intelligent Agent Technologies (IAT).

[8]  Josep Lluís de la Rosa i Esteva,et al.  A Taxonomy of Recommender Agents on the Internet , 2003, Artificial Intelligence Review.

[9]  Gediminas Adomavicius,et al.  Personalization technologies: A process-oriented perspective , 2006, Wirtschaftsinf..

[10]  Chia-Lung Hsieh,et al.  Toward Better Recommender System by Collaborative Computation with Privacy Preserved , 2011, 2011 IEEE/IPSJ International Symposium on Applications and the Internet.

[11]  Hubert Kadima,et al.  Toward ontology-based personalization of a recommender system in social network , 2010, 2010 International Conference of Soft Computing and Pattern Recognition.