Big Data Analytics in Library to Classification Book Publishers

Abstract

The library is a place for people to read books and a place that has various kinds of books to read. In the library has a lot of data from borrower data, library membership data, book data, and book return data. Therefore, big data is needed to process these data. Big data is data that contains a lot of information in various forms. This big data also has 3 characteristics, namely volume, velocity, and variation. Data mining is analyzing data using various methods and producing useful information for companies or organizations. The method used in this analysis is a decision tree classification method. Classification is the process of analyzing data by predicting and classifying data so that it can produce useful information. The application used in this analysis is the Rapidminer Studio application. This application is an application that is used to analyze data and generate information from the data analysis. The purpose of this study was to analyze book data according to the publisher and the year the book was published. This decision tree method will be used to predict book data based on the publisher and year of publication. To test data accuracy using cross validation. The results of the test show that the data accuracy rate is 40.52% with the prediction results of Gramedia Pustaka Utama 30.00%; prediction results of Elex Media Komputindo 40.78%; the results of the library span prediction 0.00%; Grasindo prediction results 45.07%; and the prediction of Andi Publisher 38.10%.