Research Article
A new approach for credit card fraud detection using Machine Learning
@INPROCEEDINGS{10.4108/eai.16-4-2022.2318073, author={Mitul Biswas and Swapan Debbarma}, title={A new approach for credit card fraud detection using Machine Learning}, proceedings={Proceedings of The International Conference on Emerging Trends in Artificial Intelligence and Smart Systems, THEETAS 2022, 16-17 April 2022, Jabalpur, India}, publisher={EAI}, proceedings_a={THEETAS}, year={2022}, month={6}, keywords={machine learning fraud detection credit card fraud smote}, doi={10.4108/eai.16-4-2022.2318073} }- Mitul Biswas
Swapan Debbarma
Year: 2022
A new approach for credit card fraud detection using Machine Learning
THEETAS
EAI
DOI: 10.4108/eai.16-4-2022.2318073
Abstract
The financial industry is growing at a rapid pace, and as a result, banking online transactions are on the rise as the government promotes digital transactions. Debit or credit cards have been used for the majority of financial transactions. As a result, the fraud associated with it is also on the rise. However, our current machine learning approach is unable to correctly detect fraudulent transactions since present fraud detection machine learning algorithms are taught and then evaluated on extremely unbalanced data sets, reducing their performance in real-world circumstances. In this paper, we proposed an algorithm that may work better after converting these imbalanced data set into balanced data set by using the oversampling technique so that system is not biased when the algorithm is actually implemented. The results show that the Random Forest algorithm with SMOTE performs better with the ability to identify more than 80% of fraud transactions.
