IP2EF: An Open-source Solution for Analyzing and Enhancing the Game Player Engagement

The integration of Artificial Intelligence (AI) has significantly transformed the gaming industry, particularly in the areas of player analytics, personalization, and interactive gameplay. Despite these advancements, current AI-driven solutions often remain closed-source or highly restrictive, limiting broader community contribution and customization. This research proposes a scalable, open-source framework named IP2EF (Interactive Player Engagement Enhancement Framework), that utilizes machine learning techniques to process gameplay data and deliver personalized feedback through an AI-powered chat-bot. The system employs algorithms such as Support Vector Machines (SVMs), K-Means Clustering, and Isolation Forests for behavior analysis, anomaly detection to recognize potential issues in players’ actions, and tailored recommendations according to actions taken by the player. The chatbot, built using RASA, presents actionable insights to players, aiming to enhance motivation. Evaluated using an open-source racing game, the framework demonstrates its ability to bridge the gap between data analytics and real-time interactivity, offering a personalized and adaptive gaming experience. The study also highlights futuristic potential opportunities to integrate large language models (LLMs) and expand the dataset for improved recommendation-based gaming systems.