Profiling Players with Engagement Predictions
arXiv:1907.03870 · doi:10.1109/CIG.2019.8848074
Abstract
The possibility of using player engagement predictions to profile high spending video game users is explored. In particular, individual-player survival curves in terms of days after first login, game level reached and accumulated playtime are used to classify players into different groups. Lifetime value predictions for each player---generated using a deep learning method based on long short-term memory---are also included in the analysis, and the relations between all these variables are thoroughly investigated. Our results suggest this constitutes a promising approach to user profiling.
Accepted for IEEE Conference on Games (CoG) 2019