A Fraud Detection System Using Decision Trees Classification in An Online Transactions

Abstract

Individuals and businesses are frequently seen engaging in a fraud scheme, which results in the loss of funds, rights, and assets. This paper aims to provide an empirical analysis and study of a supervised learning technique, decision trees (DT), on a credit card transaction dataset as a benchmark. The proposed approach can be employed to reduce FPs and FNs through supervised machine learning (ML) technique. The fraud detection system also uses historical data to construct a training set and then analyses it to identify fraudulent activity. In this study, suspicious activity is detected using the decision tree classifier. The obtained results showed that FPs and FNs in an online transaction or activity can be reduced to a large extent using DT classification. This method achieved a promising result in terms of performance measures such as precision (99.7%), accuracy (92.25%), recall (81.49%), and F1_score (86.47%) respectively. As a result, the use of ML classifiers can reduce FPs and FNs, increasing customer satisfaction in an online transaction.