Credit Card Fraud Detection Using Machine Learning As Data Mining Technique release_5ge6gagnqzb2rgzfb2z4hev57m

by Shu Ong, Saravanan Yee, Nurul Sagadevan, Hassain Ahamed, Malim

Released as a article-journal .


The rapid participation in online based transactional activities raises the fraudulent cases all over the world and causes tremendous losses to the individuals and financial industry. Although there are many criminal activities occurring in financial industry, credit card fraudulent activities are among the most prevalent and worried about by online customers. Thus, countering the fraud activities through data mining and machine learning is one of the prominent approaches introduced by scholars intending to prevent the losses caused by these illegal acts. Primarily, data mining techniques were employed to study the patterns and characteristics of suspicious and non-suspicious transactions based on normalized and anomalies data. On the other hand, machine learning (ML) techniques were employed to predict the suspicious and non-suspicious transactions automatically by using classifiers. Therefore, the combination of machine learning and data mining techniques were able to identify the genuine and non-genuine transactions by learning the patterns of the data. This paper discusses the supervised based classification using Bayesian network classifiers namely K2, Tree Augmented Naïve Bayes (TAN), and Naïve Bayes, logistics and J48 classifiers. After preprocessing the dataset using normalization and Principal Component Analysis, all the classifiers achieved more than 95.0% accuracy compared to results attained before preprocessing the dataset.
In text/plain format

Archived Files and Locations

application/pdf  722.6 kB
file_tcgacx62kvgzplr4kugx4e53sq (webarchive) (web)
Read Archived PDF
Preserved and Accessible
Type  article-journal
Stage   unknown
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: cdd20f98-3042-4b01-83b5-a880947bb5f9