IEEE

Performance Analysis of Cost-Sensitive Oversampling Mechanisms for Credit Card Fraud Detection

Abstract: Credit card fraud detection presents a persistent challenge due to severe class imbalance and the high costs associated with undetected fraudulent transactions. While oversampling techniques ...
IEEE

Complicated Imbalanced and Overlapped Data Oversampling Approach via Hypersphere Coverage and Adaptive Differential Evolution for Anomaly Detection of Industrial Internet of Things

Abstract: Anomaly detection is a unique type of classification challenge. The coupling of imbalance, overlap, and other complexity of the data, such as noise in industrial Internet of Things (IIoT) ...
GitHub

Network Intrusion Detection on NSL-KDD

A supervised machine learning project that classifies network connections as normal traffic or one of four attack families (DoS, Probe, R2L, U2R) using the NSL-KDD dataset. It also supports a simpler ...
GitHub

Network Intrusion Detection on NSL-KDD

Running it python src/eda.py # class distribution and correlation plots python src/train.py --target category # 5-class, LightGBM with 5-fold CV (default) python src/train.py --target is_attack # ...