Framework for intelligent prediction of the mobile players retention

The paper presents the novel approach for the analysis of the mobile game players’ data to predict retention, i.e. duration of remaining inside the game. The definition and measures of evaluating retention from the mobile game perspective are described. The architecture of the implemented system is presented with the detailed explanation of the subsequent (specifically data collection and processing) modules. Three specific problems related to the retention analysis (focused on the gameplay duration and making financial transactions using actual currency) are presented. Task-oriented evaluation measures (to learn about the accuracy of the proposed approach) are described. Experiments regarding the efficiency of the proposed approach using the data set from the My Spa Resort mobile game from CherryPick Games company are presented, proving usefulness of the approach. Future prospects of the solution and technical limitations are described.