6th International ICST Conference on Collaborative Computing: Networking, Applications, Worksharing

Research Article

Enhancing personalized ranking quality through multidimensional modeling of inter-item competition

Download522 downloads
  • @INPROCEEDINGS{10.4108/icst.collaboratecom.2010.14,
        author={Qinyuan Feng and Ling Liu and Yan (Lindsay) Sun and Ting Yu and Yafei Dai},
        title={Enhancing personalized ranking quality through multidimensional modeling of inter-item competition},
        proceedings={6th International ICST Conference on Collaborative Computing: Networking, Applications, Worksharing},
        publisher={IEEE},
        proceedings_a={COLLABORATECOM},
        year={2011},
        month={5},
        keywords={Collaboration Communities Concrete Gallium Irrigation USA Councils},
        doi={10.4108/icst.collaboratecom.2010.14}
    }
    
  • Qinyuan Feng
    Ling Liu
    Yan (Lindsay) Sun
    Ting Yu
    Yafei Dai
    Year: 2011
    Enhancing personalized ranking quality through multidimensional modeling of inter-item competition
    COLLABORATECOM
    ICST
    DOI: 10.4108/icst.collaboratecom.2010.14
Qinyuan Feng1,2,*, Ling Liu2,*, Yan (Lindsay) Sun3,*, Ting Yu4,*, Yafei Dai1,*
  • 1: Peking University, Beijing, China
  • 2: Georgia Institute of Technology, Atlanta, GA, USA
  • 3: University of Rhode island, Kingston, RI, USA
  • 4: North Carolina State University, Raleigh, NC, USA
*Contact email: fqy@pku.edu.cn, lingliu@cc.gatech.edu, yansun@ele.uri.edu, tyu@ncsu.edu, dyf@pku.edu.cn

Abstract

This paper presents MAPS - a personalized Multi-Attribute Probabilistic Selection framework - to estimate the probability of an item being a user's best choice and rank the items accordingly. The MAPS framework makes three original contributions in this paper. First, we capture the inter-attribute tradeoff by a visual angle model which maps multi-attribute items into points (stars) in a multidimensional space (sky). Second, we model the inter-item competition using the dominating areas of the stars. Third, we capture the user's personal preferences by a density function learned from his/her history. The MAPS framework carefully combines all three factors to estimate the probability of an item being a user's best choice, and produces a personalized ranking accordingly. We evaluate the accuracy of MAPS through extensive simulations. The results show that MAPS significantly outperforms existing multi-attribute ranking algorithms.