Detection of Credit Card Fraud using Machine Learning and Deep Learning: A Review


  • Sejal Kharat
  • Sakshi Taur
  • Rucha Khalate
  • Kimaya Kate


Fraud detection, Machine Learning, Deep Learning, Decision Tree, Logistic Regression, Convolution Neural Network.


Nowadays use of credit card is increased due to virtual world, along with its usage there is rapid growth in its misuse and fraud. There are different types of credit card frauds which needs to be identified. Such frauds lead to many financial losses for the card owner as well as for the company. The main aim is to identify whether a particular transaction is a fraud or not. For detecting fraud there is need to access public data, high class imbalance data, change in fraud nature and high false alarm rate. There are many machines learning based approaches like Extreme Learning Method, Decision Tree, Random Forest, Support Vector Machine, Logistic Regression and XG Boost. To get more accurate results state of art deep learning algorithms are applied. Analysis of both machine learning and deep leaning algorithms was done to attain meticulous result. The detailed evaluation of European card benchmark is carried out to identify the fraud transactions. Initially machine learning algorithms were applied to the dataset which has increased the accuracy of detecting fraud and later deep learning algorithms were applied to get precise results. Convolution Neural Network (CNN), a deep learning algorithm was applied to enhance the performance. A comprehensive empirical analysis has been carried out by applying variations in the number of hidden layers, epochs and applying the latest models. By performing experiments and balancing the data the false negative rate is also minimized. The main motive is fraud identification.


Download data is not yet available.




How to Cite

Sejal Kharat, Sakshi Taur, Rucha Khalate, & Kimaya Kate. (2023). Detection of Credit Card Fraud using Machine Learning and Deep Learning: A Review. International Journal of Progressive Research in Science and Engineering, 4(5), 80–83. Retrieved from