Machine learning based library management system
A novel model for predicting the availability of books in libraries is proposed using several machine learning methods and comparing their performance to select the best way to overcome the incomplete data problem.
Abstract
Many people use the Library Management System daily, yet many cannot access books in real-time. For a user, having a system that can forecast the availability of issued books would be pretty helpful. Data from the library is utilized in this study to indicate when a reader will be available. Keres and SKlearn compare random forest, support vector, and neural network results. The study's findings suggest that the availability of published books may be tracked and managed. Using the model learned, it is possible to anticipate when a reader will be available. Because of this, it is less accurate to analyze data from incomplete libraries. This research uses automated techniques for predicting library system books and using real-world library data and improved prediction models. Utilize A latent component model to rebuild the missing data to overcome the incomplete data problem. This paper proposes a novel model for predicting the availability of books in libraries using several machine learning methods and comparing their performance to select the best way.