Building Recommender Systems for Video Games on Steam. In Data Science & Engineering Master of Advanced Study (DSE MAS) Capstone Projects

MAS DSE Group 4 Capstone project: Building Recommender Systems for Video Games on Steam The goal of this project was to build a recommender system for video games on Steam. We used the Bayesian Personalized Ranking algorithm on game ownership data to construct a model that would recommend games for users to buy. On top of that, we focused on a variety of data analysis tasks to look at how well the model atacks the cold start problem and how well genre classification corresponds with user purchase patterns.

MAS DSE第4小组结项项目：Steam平台游戏推荐系统构建
本项目旨在搭建面向Steam平台的游戏推荐系统。我们采用贝叶斯个性化排序（Bayesian Personalized Ranking）算法，基于游戏拥有数据构建模型，为用户推荐可购买的游戏。此外，本项目还开展了多项数据分析任务，以探究该模型解决冷启动（cold start）问题的效果，以及游戏品类分类结果与用户购买模式的契合程度。