Implementation of Data Mining Algorithm C4.5 to Predicte Loan Payments in the Harum Manis Women's Union in Sirnoboyo Village

Abstract

The women's union, "Harum Manis" is an active savings and loan cooperative that uses members' funds in savings and loans. Given the large number of prospective members who register each year, the union still needs to be more selective in accepting prospective members who only see from work and salary, thus causing lousy credit. To reduce the occurrence of bad loans, predicting prospective members' smooth payment status and finding prospective members, including bad credit or current loans, is necessary. This research applies classification data mining techniques using the Decision Tree C4.5 method to determine the smooth payment class, which is a jam class or a smooth class. The attributes used in this study consist of four variables, namely age, marital status, income, and home status. System testing is done three times testing. The data were taken from 102 data for the "Harum Manis" Women's Union Member Loan data. Based on the test results, it was found that the first test produced the highest accuracy, reaching 64%.