A Comparative Analysis Of Collaborative Filtering Models For Game Recommendation Using Cosine Similarity, SVD, K-Means Clustering And Real-Time Game Insights

Abstract

This paper presents a study on GameRS, a game recommendation system that employs collaborative filtering techniques, including Cosine Similarity, Singular Value Decomposition (SVD), and K-means. Clustering, in conjunction with real-time game insights facilitated by Groq AI. The system integrates data from the RAWG API to provide game recommendations and dynamically retrieves game details, including genres, platforms, reviews, ratings, release dates, trailers, and gameplay mechanics. Furthermore, it presents a novel User Satisfaction Index for Games (USIG), a metric designed to assess anticipated enjoyment by considering factors such as rating, genre similarity, and platform similarity. Users may pose specific inquiries related to games, to which Groq AI provides succinct and accurate answers. GameRS, developed with Streamlit, manages both the front-end interface and back-end logic, allowing users to access recommendations, game details, trailers, and additional features. Evaluation results indicate that Cosine Similarity surpasses alternative methods regarding recall and hit rate, whereas SVD and K-means provide insights into latent user preferences and clustering behaviors.