Open AccessDesign The Modified Multi Practical Swarm Optimization To Enhance Fraud Detection
Author(s) -
Zainab Khamees Muter,
Abeer Tariq Molood
Publication year - 2020
Publication title -
mağallaẗ ibn al-haytam li-l-ʻulūm al-ṣirfaẗ wa-al-taṭbīqiyyaẗ/ibn al-haitham journal for pure and applied sciences
Language(s) - English
Resource type - Journals
eISSN - 2521-3407
pISSN - 1609-4042
DOI - 10.30526/33.2.2425
Subject(s) - credit card fraud , credit card , computer science , support vector machine , data mining , machine learning , payment , world wide web
Financial fraud remains an ever-increasing problem in the financial industry with numerous consequences. The detection of fraudulent online transactions via credit cards has always been done using data mining (DM) techniques. However, fraud detection on credit card transactions (CCTs), which on its own, is a DM problem, has become a serious challenge because of two major reasons, (i) the frequent changes in the pattern of normal and fraudulent online activities, and (ii) the skewed nature of credit card fraud datasets. The detection of fraudulent CCTs mainly depends on the data sampling approach. This paper proposes a combined SVM- MPSO-MMPSO technique for credit card fraud detection. The dataset of CCTs which consists of 284,807 transactions performed by European cardholders in 2013 was used in this study. The proposed technique was applied to both the raw dataset and the pre-processed dataset. The performance of these techniques is evaluated based on accuracy, and the fastest time it takes to detect fraud. This paper, proposed a technique that uses SVM, MPSO and MMPSO to form an ensemble for the detection of credit card fraud