Improving User Retention in Video Game Industry

This research paper delves into the intersection of player data analytics and affective computing to predict and adapt game difficulty levels for the purpose of enhancing player retention in the gaming industry.

This research paper delves into the intersection of player data analytics and affective computing to predict and adapt game difficulty levels for the purpose of enhancing player retention in the gaming industry. The study used two Kaggle datasets which include a facial emotion dataset and real-time call of duty player data. A novel emotion detection model, leveraging transfer learning, is constructed to discern a spectrum of emotions from player facial expressions. The emotional context extracted from this model is seamlessly integrated with player data, facilitating a supervised learning task centered on predicting changes in game difficulty levels—a pivotal factor in player engagement. Several machine learning models including K-Nearest Neighbors, Decision Trees, Random Forests, MLP Classifiers, AdaBoost, and Gaussian Naive Bayes were employed to use emotion and player data to predict difficulty changes that will raise player retention.

Explore More!

Research Paper