Title:
Credit Card Fraud Detection Model Using Deep Learning

Authors:
Seun Mayowa Sunday, United Kingdom

Abstract:

The ever-evolving state of technology is responsible for a wide variety of advances. In this article, we discuss online transactions that are conducted using credit cards, which might result in credit card fraud. The purpose of this research is to discuss the development of a system that can identify credit card fraud by making use of deep learning neural networks (DNN).
 
Because of the skewness in the dataset, even if the Neural Network (NN) is trained using a huge number of iterations, it will not be accurate enough to determine whether or not the data represents fraudulent or non-fraudulent activity. This study makes use of a variety of pre-processing methods for the data, such as the elimination of null entries, the correction of imbalanced data, and others. After that, the author proceed to the methods for feature selection, which is later followed by feature engineering in order to carry out normalisation prior to the development of the model. The results that were obtained indicate that the use of these methods improves the accuracy of the prediction process, which is then evaluated in relation to the work that has been done previously in the same field.

DOI: http://dx.doi.org/10.51505/ijaemr.2025.1523