Design of a Recommender System for Video Games based on In-Game Player Profiling and Activities

The use of recommender systems has a large diffusion in the e-commerce and entertainment services. These systems try to suggest to the users a personalized set of other items or products, likely to be of interest and compatible to their preferences. Usually, a combination of collaborative filtering and/or content-related information is used to determine a set of suggested items. Due to the relevant growth of the video game industry in the last years, the study for advanced recommender systems for video games has seen an increasing interest. In this paper, we propose a novel approach to design a recommender system for video games, based on an in-game profiling of the player, and on a novel taxonomy of the game activities. The implementation of the proposed approach requires a deep integration with the game design and level design activities. We present in detail the approach, and the results obtained using a prototype video game to validate the proposed recommender system.