Personalization in Media Delivery Platforms

Research Article

Optimal Ranking for Video Recommendation

Download
312 downloads
  • @INPROCEEDINGS{10.1007/978-3-642-12630-7_30,
        author={Zeno Gantner and Christoph Freudenthaler and Steffen Rendle and Lars Schmidt-Thieme},
        title={Optimal Ranking for Video Recommendation},
        proceedings={Personalization in Media Delivery Platforms},
        proceedings_a={PERMED},
        year={2012},
        month={10},
        keywords={},
        doi={10.1007/978-3-642-12630-7_30}
    }
    
  • Zeno Gantner
    Christoph Freudenthaler
    Steffen Rendle
    Lars Schmidt-Thieme
    Year: 2012
    Optimal Ranking for Video Recommendation
    PERMED
    Springer
    DOI: 10.1007/978-3-642-12630-7_30
Zeno Gantner1,*, Christoph Freudenthaler1,*, Steffen Rendle1,*, Lars Schmidt-Thieme1,*
  • 1: University of Hildesheim
*Contact email: gantner@ismll.de, freudenthaler@ismll.de, srendle@ismll.de, schmidt-thieme@ismll.de

Abstract

Item recommendation from implicit feedback is the task of predicting a personalized ranking on a set of items (e.g. movies, products, video clips) from user feedback like clicks or product purchases. We evaluate the performance of a matrix factorization model optimized for the new ranking criterion BPR-Opt on data from a BBC video web application. The experimental results indicate that our approach is superior to state-of-the-art models not directly optimized for personalized ranking.