<![CDATA[Libraries, as essential information centers, play a crucial role in providing diverse resources to meet the information needs of visitors. In the digital age, libraries face challenges in efficiently managing their vast collections while offering personalized services that cater to the varying needs of users. The primary goal of this research is to improve the management of library resources by developing a personalized book recommendation system. This system aims to provide relevant book suggestions based on individual preferences, specifically tailored to the academic needs and interests of university students. To achieve this, the research applies a combination of User-Based Collaborative Filtering (UBCF) and k-Nearest Neighbors (k-NN) algorithms, which are powerful techniques in the field of data mining. These methods are used to analyze the academic performance (measured by the students' Indeks Prestasi Semester (IPS) scores) and book preferences to create a personalized recommendation system. The study demonstrates that the integration of UBCF and k-NN significantly enhances the accuracy and relevance of book recommendations, providing students with more tailored suggestions based on their academic achievements and preferences. The results indicate that such a recommendation system not only improves the user experience but also contributes to the enhancement of students' academic performance by offering them books that align with their learning needs, ultimately supporting the academic goals of higher education institutions.]]>
