Design and Implementation of A Students’ Library Management System Using Random Forest Technique

Abstract

The increasing acceptance of digital technologies within higher educational institutions has transformed the administration and accessibility of academic resources. Despite the availability of digital library platforms, many existing systems provide only basic search functionalities and lack intelligent mechanisms capable of recommending relevant learning materials to students. Consequently, students often experience challenges in locating suitable academic resources, resulting in information overload and inefficient utilization of available library collections. This study presents the design and implementation of a Student Library Management System using the Random Forest technique for automated academic resource recommendation. The technique accepted in this study incorporates system analysis and design principles together with machine learning techniques. The implementation process involved data collection and preprocessing, feature extraction and selection, Random Forest model training, testing, validation, and integration of the recommendation engine into the web-based library management platform. Experimental evaluation of the developed system was performed; the model attained an accuracy of 90%, precision of 92%, recall of 90%, F1-score of 90%, and AUC-ROC of 94%, indicating the reliability of the technique. These findings demonstrate that the Random Forest algorithm provides reliable recommendation performance and improves accessibility to academic resources within digital library environments.