Analisis Perbandingan Performa Algoritma Machine Learning dalam Mendeteksi Fraud pada Perbankan

Abstract

This study aims to analyze and compare the performance of various machine learning algorithms in detecting fraud activities in the banking sector. With the increasing frequency and complexity of fraud, the need for effective detection systems becomes crucial. This study uses a dataset from an external data provider containing banking transactions labeled as fraud or non-fraud. The machine learning algorithms compared include Logistic Regression, Decision Trees, Random Forest, and Gradient Boosting. This study contributes to a better understanding of the strengths and weaknesses of various machine learning algorithms in the context of banking fraud detection. The results of this study are expected to help financial institutions select and implement the most effective machine learning solutions to minimize fraud risk. These findings also provide insights for further development in machine learning-based banking security.