Identification of Fraudulent Credit Card transactions using Machine Learning Algorithms
Pranaav Jadhav, Urvashi Lalwani, Ayush Gour, Mohammad Shayan, Shubham Motwani · 2022 IEEE 7th International conference for Convergence in Technology (I2CT) · 2022
Ever since the existence of e commerce payments systems came into being, people have found new ways to access someone’s credentials illegally. This is a major issue in current era as more and more transactions are being done online. Every year fraud cost generated in the economy is more than $4 trillion internationally. This is not surprising, as the return on investment for fraud detection and prevention is massive. Cybercrime specialists estimate that an investment of 1 million dollars into fraud or attack can net up to$100 million. Financial institutions such as commercial and investment banks operations are increasingly being targeted and require some method to handle and support the progress of credit card fraud detection. To avoid fraud and to secure transactions systems they require some advanced technology that support the use of artificial intelligence (AI) and machine learning (ML) approaches to stay one step ahead of criminals. Being a classification type problem, we propose a ML model incorporating XGBoost algorithm along with SMOTE analysis. Our aim is to minimize the number of fraudulent transactions being predicted as legitimate transactions as the gravity of these type of errors outweighs that of the other in a real world scenario.