Comparison of K-Nearest Neighbor, Naive Bayes Classifier, Decision Tree, and Logistic Regression in Classification of Non-Performing Financing

Rizky Putra (Institut Teknologi Sepuluh Nopember)
Iis Dewi Ratih (Institut Teknologi Sepuluh Nopember)

International Journal of Advanced Science and Computer Applications
Vol. 2 No. 2: September 2023

The Non-Performing Financing (NPF) indicator of one of the Islamic Banks in Indonesia in the 1st to 3rd quarter of 2021 in a row of 9.69%; 9.97%; 9.46%. The NPF movement tends to improve slightly from time to time but still exceeds the maximum limit stipulated in Bank Indonesia’s Regulation Number 23/2/PBI/2021, which is no more than 5%. This shows that the Islamic bank has a financing performance that can be said to be less good. Preventive steps that can be taken to reduce the NPF ratio in order to improve the health of the bank is to classify prospective financing customers. This research was conducted using the K-Nearest Neighbor (KNN), Naive Bayes Classifier (NBC), Decision Tree, and Logistics Regression classification methods to predict potential financing customers. The dataset is divided into 80% training and 20% testing. It was found that the best classification result was the Naive Bayes Classifier in the proportion of distribution of 80% training data and 20% testing data with an accuracy value of 84.69%, sensitivity of 58.25%, and specificity of 90.16%.