Use of K-Means Clustering Method for Books Data in Acharya Raghuveer Library, Central University of Himachal Pradesh, Dharamshala, India

Purpose- The study formulates clusters of Library and Information (LIS) discipline books from Acharya Raghuveer Library, Central University of Himachal Pradesh. Cluster formulation aims to identify the utilization rate of books. Furthermore, the study attempts to find the direction for collection management and developing related services for the users in the library. Design/methodology/approach- Books circulation data set is obtained, formatted and made compatible for further analysis. The Euclidean distance formula is used to find the distance between two points on a plane. Afterwards, the K-means clustering algorithm is implemented to generate the required clusters. Findings- Three clusters of books namely, Frequently Borrowed books (C1), Rarely Borrowed Books (C2) and Most Frequently Borrowed Books (C3) are derived. Out of a total of 30 book records, 19 books are grouped as often borrowed books, 6 books are grouped as rarely borrowed books and 5 books are grouped as most frequently borrowed books. Originality/value- The study points out the importance and applicability of data analysis to examine the patterns of resource usages in libraries. Further comprehensive study with data analysis may give directions for collection development and management in libraries