Using isolation forest in anomaly detection: The case of credit card transactions

Soumaya Ounacer,Mohamed Yassine Ghoumari,Mohamed Azzouazi,Hicham Ait El Bour,Younes Oubrahim

doi:10.21533/pen.v6i2.533

Soumaya Ounacer, Mohamed Yassine Ghoumari + Show 3 more

Open Access

https://doi.org/10.21533/pen.v6i2.533

Copy DOI

Abstract

With the evolution of new technology especially in the domain of e-commerce and online banking, the payment by credit card has seen a significant increase. The credit card has become the most used tool for online shopping. This high rate in use brings about fraud and a considerable damage. It is very important to stop fraudulent transactions because they cause huge financial losses over time. The detection of fraudulent transactions is an important application in anomaly detection. There are different approaches to detecting anomalies namely SVM, logistic regression, decision tree and so on. However, they remain limited since they are supervised algorithms that require to be trained by labels in order to know whether the transactions are fraudulent or not. The goal of this paper is to have a credit card fraud detection system which is able to detect the highest number of new transactions in real time with high accuracy. We will also compare, in this paper, different unsupervised techniques for credit card fraud detection namely LOF, one class SVM, K-means and Isolation Forest so as to single out the best approach.

Highlights

Given the high number of purchases made daily using the credit card, the risk of fraudulent transactions arises at any time
In order to recognize fraudulent transactions made by the credit card, we will apply anomaly detection
Detection is an important problem in a wide range of application domains and research areas such as health diagnosis, system intrusion in cyber-security, credit card fraud detection, e-commerce[1]and fault tolerance in industry and so on

Summary

Introduction

Given the high number of purchases made daily using the credit card, the risk of fraudulent transactions arises at any time. In order to recognize fraudulent transactions made by the credit card, we will apply anomaly detection. Many anomaly detection methods, supervised and unsupervised, have been applied to credit card fraud. The majority of works in detecting fraudulent transactions of credit card deals with supervised techniques[5]. The objective of this work is to identify whether new transactions are fraudulent or not by using the isolation forest technique which helps in minimizing the number of false positives and detecting the highest number of fraud in credit card transactions. This paper is organized as follows: In the first section, we will discuss some related works in the case of credit card fraud and we will compare different unsupervised methods that identify anomalies in the credit card transactions. We will conclude this paper with a conclusion and give some ideas for future work

Related Works

Credit card fraud detection techniques

Isolation Forest

Findings

Conclusion