The Implementation and Preliminary Verification of an Optimized VR Games Recommendation System

This study implements an optimal VR game products recommendation system for players by collecting user physiological information and providing recommendations based on big data analysis. In a predefined testing scenario, the system first automatically gathers users' physiological and response signals (such as heart rate, blood pressure, hand/foot movement speed, response time to stimuli, speed/accuracy of answering questions, etc.) through sensors worn by players to understand the user's response state to specific stimuli. Then, after data analysis, it can provide game product manufacturers with recommendations tailored to the player, ensuring that the recommended products truly match the user's skills, preferences, and expectations. Experimental results show that with the recommendation function of this system, the probability of users purchasing games that are not suitable for them is significantly reduced, leading to a more satisfying product experience for users. This kind of experience improvement can effectively enhance user experience in various application areas such as learning and entertainment, and greatly benefit product promotion for manufacturers.