Data Analytics in the Electronic Games

Abstract

This paper aims at the use of data analytics methods in mobile games. The main goal was to predict future purchases of players in the selected mobile game. The result presents the information about whether the player is going to buy any of the offered bonus packages or not. This information is crucial for marketing and possible ways of monetization. From the perspective of data analytics, the goal is the creation of a classification model in line with the CRISP-DM methodology. We used the following algorithms in the modeling phase: Random forest, Naive Bayes, Linear regression, XGBoost, and Gradient Boosting. All generated models were evaluated by contingency tables, which presented models accuracy as the ration between successfully predicted values to all predicted samples. The results are plausible and have the potential to be deployed into practice as a baseline model or support for personalized marketing activities.