GEC Student Work

A Game Recommendation Method Based on Machine Learning

Abstract: The emergence and popularity of the Internet have brought users a large amount of information to meet their information needs. Still, the rapid development of the Internet has brought about a significant increase in the amount of online information, making it impossible for users to obtain the part of the information that is useful to them. The efficiency of using information has been reduced instead. This is when a recommender system is needed to recommend the content of interest to users based on their information. Any website or platform has its own independent recommender system, and collaborative filtering is one of the traditional recommender algorithms. This paper uses steam’s users’ data to cluster and label separately to create four different collaborative filtering game-recommender models based on historical purchases, game time, and the relationship between items. They then compare their advantages and disadvantages to determine which model is more suitable for game recommender systems.