12th EAI International Conference on Testbeds and Research Infrastructures for the Development of Networks & Communities

Research Article

Implicit Feedback Recommender System Based on Matrix Factorization

Download11 downloads
  • @INPROCEEDINGS{10.4108/eai.28-9-2017.2273855,
        author={Na Jiang},
        title={Implicit Feedback Recommender System Based on Matrix Factorization},
        proceedings={12th EAI International Conference on Testbeds and Research Infrastructures for the Development of Networks \& Communities},
        publisher={EAI},
        proceedings_a={TRIDENTCOM},
        year={2018},
        month={1},
        keywords={recommendation system matrix decomposition implicit feedback},
        doi={10.4108/eai.28-9-2017.2273855}
    }
    
  • Na Jiang
    Year: 2018
    Implicit Feedback Recommender System Based on Matrix Factorization
    TRIDENTCOM
    EAI
    DOI: 10.4108/eai.28-9-2017.2273855
Na Jiang1,*
  • 1: Zhaotong University
*Contact email: 27805044@qq.com

Abstract

With the development of the internet age, information overload problem is imminent. At now, almost of recommended models use the explicit feedback. But lots of implicit feedback data are missing. The paper explores the area of recommendation based on large-scale implicit feedback, Where only positive feedback is available. Further, the paper carried on the empirical research on the Implicit Feedback Recommendation Model. By maximized the probability of the user's choices, IFR mean the progress task into optimization problems In the way, the experiment results confirm the superiority of the model. However, the model is insufficient about online research and a lack of details.