Ensemble ML Based Credit Card Fraud Detection

Long gone is the time when people preferred using only cash, there isn’t anyone who is naive to how online transactions work since everyone is trying to go cashless, be it using UPI apps or credit and debit cards. The same has even led to a significant increase in the number of credit card fraud cases. So we aim to build a credit card fraud recognition system that will involve an arrangement of supervised learning algorithm. Fraudsters disguise the ordinary conduct of clients and the misrepresentation designs are changing quickly so the extortion discovery framework needs to continually learn and refresh. One of the difficulties looked during the time spent in distinguishing false transactions in the datasets. By and large, the dataset used to foster such AI models has imbalanced class circulation. It is clear that in transactions, the odds of having false exchanges are pitiful, contrasted with genuine exchanges. It prompts the imbalanced extents of marks in the dataset. In this project, I propose to develop and apply data level algorithms as well as ensemble based class imbalance solutions. The developed approach will be evaluated using highly imbalanced credit card transaction datasets in terms of improvements of accuracy, precision, recall and etc.

Built With

• python