Analisa Distance Metric Algoritma K-Nearest Neighbor Pada Klasifikasi Kredit Macet

Abstract

Data mining is a method that can classify data into different classes based on the features in the data. With data mining, non-performance loan categories can be classified based on data on lending from cooperatives to their members. This study uses K-Nearest Neighbor to classify non-performance loan categories with various distance metric variations such as Chebyshev, Euclidean, Mahalanobis, and Manhattan. The evaluation results using 10-fold cross-validation show that the Euclidean distance has the highest accuracy, precision, F1, and sensitivity values ​​compared to other distance metrics. Chebyshev distance has the lowest accuracy, precision, sensitivity, while Mahalanobis distance has the lowest F1 value. Euclidean and Manhattan distances have the highest reliability values ​​for true-positive and true-negative class classifications. Mahalanobis distance has the lowest reliability value for false-positive class classification, while Chebyshev distance has the lowest value for false-negative class classification