Credit-Card-Fraud-Detection

This Project contains the code for a Credit Card Fraud Detection project using a dataset from Kaggle, which includes 284,807 credit card transactions with only 492 frauds, is highly unbalanced. To address the class imbalance, the project implements a voting classifier and a neural network with focal loss in PyTorch, achieving an F1-score of 0.86 and 0.85 PR_AUC for the positive class (fraud).