Machine Learning Based Personalized Recommendation Engine for Book Rent using Collaborative Filterings

In the digital era, recommender systems have become essential tools for providing users with personalized content tailored to their preferences. This paper presents a machine learning–based book recommendation system leveraging Collaborative Filtering (CF) techniques to enhance the reading experience by suggesting books aligned with users’ interests. The proposed system implements both User-Based and Item-Based Collaborative Filtering, as well as similarity-based measures such as Jaccard Similarity, to identify patterns in user ratings and generate accurate recommendations. By analyzing users’ past interactions and comparing them with the preferences of similar readers, the system overcomes challenges related to sparsity, cold start, and scalability inherent in traditional recommendation methods. Experimental evaluation demonstrates that the proposed approach improves recommendation accuracy and relevance, thereby providing an effective and personalized pathway for literary discovery. This work contributes to the field by integrating advanced CF techniques into book recommendation platforms, offering readers a seamless and insightful selection process.