<![CDATA[Libraries expand their book collections every year, making managing and organizing shelves increasingly challenging. This makes finding and grouping relevant books quite time – consuming, especially when the data is already quite large. Therfore, this study attemps to utilize data mining methods, specifically the K-Means algorithm, to help group books based on certain similarities, such as category and borrowing. Before the grouping process is carried out, the book data first goes through preprocessing and normalization stages to make data look neat and ready to be processed. Furthermore, the K-Means algorithm is used to generate several groups of books with similar characteristics. From the data processing results, K-Means has been proven to be able to form several fairly clear clusters, this sifnificantly assisting libraries in organizing books, providing reading recommendations, and improving the quality of service for students and lecturers. Overall, the implementations of the K-Means algorithm in this library can accelerate collection management work and support a more data – driven decision – making process.]]>
Copyrights © 2025
