Industrial Networks and Intelligent Systems. 3rd International Conference, INISCOM 2017, Ho Chi Minh City, Vietnam, September 4, 2017, Proceedings

Research Article

Program Popularity Prediction Approach for Internet TV Based on Trend Detecting

  • @INPROCEEDINGS{10.1007/978-3-319-74176-5_14,
        author={Chengang Zhu and Guang Cheng and Kun Wang},
        title={Program Popularity Prediction Approach for Internet TV Based on Trend Detecting},
        proceedings={Industrial Networks and Intelligent Systems. 3rd International Conference, INISCOM 2017, Ho Chi Minh City, Vietnam, September 4, 2017, Proceedings},
        proceedings_a={INISCOM},
        year={2018},
        month={1},
        keywords={Internet TV Popularity prediction Dynamic time warping Random forests regression Gradient boosting decision tree},
        doi={10.1007/978-3-319-74176-5_14}
    }
    
  • Chengang Zhu
    Guang Cheng
    Kun Wang
    Year: 2018
    Program Popularity Prediction Approach for Internet TV Based on Trend Detecting
    INISCOM
    Springer
    DOI: 10.1007/978-3-319-74176-5_14
Chengang Zhu,*, Guang Cheng,*, Kun Wang1,*
  • 1: Nanjing University of Posts and Telecommunications
*Contact email: cgzhu@njnet.edu.cn, gcheng@njnet.edu.cn, kwang@njupt.edu.cn

Abstract

Predicting program popularity precisely and timely is of great value for content providers, advertisers, as well as Internet TV operators. Existing prediction methods usually need large quantity of samples and long training time, while the prediction accuracy is poor for the programs that experience a high peak or sharp decrease in popularity. This paper presents our improved prediction approach based on trend detecting. First, we apply a dynamic time warping (DTW) distance based k-medoids algorithm to group programs popularity evolution into 4 trends. Then, 4 trend-specific prediction models are built separately using random forests (RF) regression. According to the features extracted from electronic program guide (EPG) and early view records, newly published programs are classified into the 4 trends by a gradient boosting decision tree. Finally, combining forecasting values from the trend-specific models and classification probability, our proposed approach achieves better prediction results. The experimental results show that, compared to the existing prediction models, the prediction accuracy can increase more than 20%, and the forecasting period can be effectively shortened.