CREDIT CARD FRAUD DETECTION USING MACHINE LEARNING ALGORITHMS

Author Name: Muhammad Zeeshan Younas

Volume: 01 &  Issue:

Country: Pakistan

DOI NO.: 08.2020-25662434, DOI Link: http://www.doi-ds.org/doilink/09.2020-97153116/

Affiliation:

Department of Computer Science, Capital University of Science & Technology, Islamabad, Pakistan

ABSTRACT

Credit card fraud is a severe issue in financial services area. Every year billions of dollars are lost due to credit card fraud. Credit card has been one of the most flourishing financial services by banks over the past years. However, with the rising number of credit card users, banks have been facing an escalating credit card default rate. Credit card fraud is linked with the prohibited usage of credit card material for acquisitions. In this research work, various machine learning classification techniques and methods are used to analyzed and predict the accuracy of credit card fraud detection. Dataset of credit card transactions is sourced from European cardholders containing 284,807 transactions. Thus, Logistic Regression, Multi-Layer Perceptron, Naïve Bayes and Random Forest are used to test the variable in predicting credit fraud and by the experimental outcomes and results it’s evident that Random Forest algorithm predicts the credit card fraud detection with the accuracy of 99.95% and also with good precision rate 100%.

Key words: Machine Learning, Classification Techniques, Credit card default, WEKA, Prediction, Analysis.