Credit Card Fraud Detection through Class Balancing Framework and Machine Learning Algorithms

Nowadays, people use credit cards for online transactions as it provides an efficient and easy-touse facility. With the increase in usage of credit cards, the capacity of credit card misuse has also enhanced. Credit card frauds cause significant financial losses for both credit card holders and financial companies. In this paper, the main aim is to detect such frauds, including the accessibility of public data, high-class imbalance data, the changes in fraud nature, and high rates of false alarm. The relevant literature presents many machines learning based approaches for credit card detection, such as Extreme Learning Method, Decision Tree, Random Forest, Support Vector Machine, Logistic Regression and XG Boost. However, due to low accuracy, there is still a need to apply state of the art deep learning algorithms to reduce fraud losses. The main focus has been to apply the recent development of deep learning algorithms for this purpose, also PCA and SMOTE are used for Feature Selection and Data Balancing. PCA is the widely used tool in data analysis and in machine learning for predictive models. It will be more called as a dimensionality reduction method, then as a feature selection method. SMOTE is commonly used oversampling methods to solve the imbalance problem. SMOTE is used to generate artificial or synthetic samples for the minority class. Comparative analysis of both machine learning and deep learning algorithms was performed to find efficient outcomes. Machine learning algorithms are applied to the dataset, which improved the accuracy of detection of the frauds.