Md Nurul Islam Chowdhury

Mitigating Class Imbalance in U.S. Financial Security: A Latent Feature Augmentation Approach for High-Purity Fraud Detection

Credit card fraud detection is challenged by extreme class imbalance (< 0.2% fraud) and non-linear fraud patterns, causing traditional supervised models to suffer from reduced sensitivity and poor interpretability. This paper proposes a hybrid model combining a sparse Deep Autoencoder (15-node bottleneck) with Random F...