Libraries at University of Nebraska-Lincoln

 

Date of this Version

Winter 1-20-2021

Abstract

The Library Management System supports numerous users every day and yet many users cannot avail books in real time for their use. For a user, it will be very beneficial to have a system which can predict the possible availability of the issued books. In this paper, Machine learning is used on the data obtained from the library to predict the date for book availability. Random forest, support vector and neural network are used and the result trend are compared using keres and SKlearn. From the study, the result shows that it is possible to know and govern the availability of the books issued. The learned model can then be used to predict the availability of the book. However, the analysis accuracy is reduced when the quality of library data is incomplete. In this study, streamline machine learning algorithms for effective prediction of books in library system is used. The experiment of the modified prediction models over real-life library data collected from Central library of Central Institute of Technology Kokrajhar (CLCITK) was used. To overcome the difficulty of incomplete data, a latent factor model to reconstruct the missing data was used. This study is a proposal for a new model using different machine learning method and to compare performance among them and to identify the more suitable method for the prediction system of book availability in libraries.

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.