Comparative Analysis of K-Means and K-Nearest Neighbor Algorithm for Telecom Fraud Detection

Abstract

This study discusses problems that often occurs, namely telecom fraud. One of them is Telkomsel as the provider and is responsible for telecommunications facilities in Indonesia. Telecom Fraud is a fraudulent activity in the service with the aim of using the service illegally by avoiding the charges used by the user and causing losses to the operator. In this study, the classification of Telkomsel's quota data was carried out using the K-Nearest Neighbor algorithm and the K-Means algorithm. And, testing the confusion matrix as a comparison of the prediction results of the algorithm. By testing the K-Means algorithm using k = 2 and obtained an accuracy value of 0.8. While the K-Nearest Neighbor has a value with a higher level of accuracy with a value of 0.99 as an accurate classification method