Deep Learning Enabled Fraud Detection in Credit Card Transactions

Submission Deadline-29th March 2024
March 2024 Issue : Publication Fee: 30$ USD Submit Now
Special Issue of Education: Publication Fee: 30$ USD Submit Now

International Journal of Research and Scientific Innovation (IJRSI) | Volume V, Issue VII, July 2018 | ISSN 2321–2705

Deep Learning Enabled Fraud Detection in Credit Card Transactions

Reshma R S#

IJRISS Call for paper

 #Research Scholar, Department of Mechanical Engineering, APJ Abdul Kalam Technological University, College of Engineering Trivandrum, Kerala, India

Abstract-Fraudulent activities exist in all fields of financial domain; credit card is not an exception. The increased fraud in credit card transaction is obviously due to its wide spread popularity since the introduction of online banking and e-commerce platforms. The purpose of the fraud may be to obtain goods without paying, or to obtain unauthorized funds from an account. We cannot rely on pattern based fraud detection since the fraudster rarely follows any pattern. As technology advances the fraudulent activities will also increase. The project aims to introduce deep learning technique to detect fraud in credit card transactions. Deep learning consists of neural networks with many hidden layers. The project uses deep learning techniques such as Autoencoder, Restricted Boltzmann Machine, Variational Autoencoder and Deep Belief Network to detect fraud in the credit card transactions. The aim is to find the best technique among them. Unsupervised deep learning method is used to evaluate fraud since the model learn from data and not from labels.

Keywords: Unsupervised Learning, Deep Learning, Autoencoder, Variational Autoencoder, Restricted Boltzmann Machine, Deep belief network

I. INTRODUCTION

Technology is advancing day by day and this improvement in technology has significant influence on various areas including financial transactions. Nowadays credit card is the most widely used transaction method, this increased popularity of credit card is mainly due to the ease of transaction, the increasing popularity of network banking and mobile banking. Since technology is a two sided coin, there is also a great improvement in the type of fraud that can occur. Fraudster keeps on changing his fraud pattern and rarely uses same pattern for fraudulent activities. This shows us that simple fraud detection method based on labelled data cannot work well with all type of fraud. Its high time we should think about unsupervised learning method where we are not bounded to the limitations of labelled data. The paper aims to develop unsupervised deep learning models to detect fraud in credit card transactions. Credit card fraud increases day by day. The way by which fraud occur rarely follows pattern. Unsupervised deep learning method can be used to detect fraud in financial transactions