Predicting long-term product ratings based on few early ratings and user base analysis
作者：
Highlights：
• A new prediction problem of predicting long-term average ratings of products is designed.
• A Bayesian network model is proposed to solve this problem.
• Performance of the proposed model is compared with the performance of five other prediction methods/models; a Linear Regression model, two variations of a Running Average predictor, an Ordered Logistic Regression model and a Confirmatory Factor Analysis model.
• Each model’s performance is evaluated using the “MovieLens” dataset. The training is done on 56,590 data points, the ratings submitted for 1155 movies, and the prediction results are reported for 495 movies.
• Applications of this problem along with future research directions are discussed.
摘要
•A new prediction problem of predicting long-term average ratings of products is designed.•A Bayesian network model is proposed to solve this problem.•Performance of the proposed model is compared with the performance of five other prediction methods/models; a Linear Regression model, two variations of a Running Average predictor, an Ordered Logistic Regression model and a Confirmatory Factor Analysis model.•Each model’s performance is evaluated using the “MovieLens” dataset. The training is done on 56,590 data points, the ratings submitted for 1155 movies, and the prediction results are reported for 495 movies.•Applications of this problem along with future research directions are discussed.
论文关键词：Machine learning,Bayesian network modeling,Product rating prediction
论文评审过程：Received 2 February 2016, Revised 7 December 2016, Accepted 21 December 2016, Available online 28 December 2016, Version of Record 7 January 2017.
论文官网地址：https://doi.org/10.1016/j.elerap.2016.12.002
