|
Abstract
|
The digital age has changed the way people access books. One of the biggest challenges is predicting the availability of books. Libraries have limited resources and often lack the ability to predict which books will be available at any given time. This can lead to frustration when readers are unable to access the books they need. In this paper, an intelligent analysis of book availability prediction has been proposed in cloud digital library management system using machine learning approach. Moreover, these predictive analytics can be used to enhance reader experience. Libraries can analyze user data to identify books that readers are likely to be interested in. This information can then be used to recommend books to users, increasing the likelihood that they will find the books they are looking for. The use of this predictive analytics in digital libraries has great potential to improve user experience and increase book availability. By leveraging the power of data mining algorithms, libraries can gain a better understanding of reader demand and make more informed decisions about which books to stock. the proposed book availability prediction model (BAPM) has reached 82.92% of Fowlkes–Mallows index rate, 83.83% of bookmaker informedness, 97.46% of Delta-P and 93.03% of Matthews’s correlation coefficient. This can ultimately lead to a more satisfying experience for readers and more efficient use of resources for IoT enabled libraries.
|