Item Recommendation Using Collaborative Filtering in Mobile Social Games: A Case Study

This paper evaluates the performance of collaborative filtering in mobile social game. The evaluation involves both user-based and item-based collaborative filtering on game items for in-app purchases, and including 4 different social information available in the game. Based on the operational data from a mobile social game, Barcode Footballer, with more than 100k users and 50k purchasing history, it is concluded that both user-based and item-based collaborative filtering have much higher precision than random recommendation, while user-based approach with friendship as similar relationship has better performance than original approach. This paper also proposes a hybrid method to improve the performance of user-based friendship approach. The results can be applied to mobile social games to recommend highly needed items to users so that the monetization can be enhanced.