篇名 | IPTV User’s Complaint Prediction Based on the Gaussian Mixture Model for Imbalanced Dataset |
---|---|
卷期 | 28:6 |
作者 | Xin Wei 、 Zhilin Li 、 Ronghua Liu 、 Liang Zhou |
頁次 | 216-224 |
關鍵字 | GMM 、 imbalanced IPTV dataset 、 Naïve Bayes classifier 、 over-sampling 、 EI 、 MEDLINE 、 Scopus |
出刊日期 | 201712 |
DOI | 10.3966/199115992017122806019 |
IPTV user’s experience is vital for operators to continually enhance their quality of content service and transmission. User’s complaint is closely related to user’s quality of experience (QoE). Predicting user’s potential complaint in time is necessary. However, the happening probability of complaint is far less than that of the normal circumstances, leading to the imbalanced dataset. In order to handle this issue, an over-sampling method based on the Gaussian mixture model (GMM) is proposed. Specifically, GMM is adopted to describe the distribution of limited complaint samples. After estimated the parameters in this model, new minority class samples can be generated, which is more representative than the traditional Synthetic Minority Oversampling Technique (SMOTE). Then the Naïve Bayes classifier is used for finishing classification and prediction. Experimental results show that the proposed algorithm performs better than the competing algorithms in predicting user’s complaint.