Western-OC2-Lab/AutoML-Implementation-for-Static-and-Dynamic-Data-Analytics

Automates the entire ML pipeline—data preprocessing, feature engineering, model selection, and hyperparameter optimization—using Bayesian optimization (BO-TPE), particle swarm optimization, and grid search across algorithms like LightGBM, random forests, and Hoeffding trees. Includes specialized online learning implementations with concept drift detection via River and adaptive methods (Adaptive Random Forest, Leveraging Bagging) for streaming IoT data. Provides end-to-end case studies on network intrusion detection (CICIDS2017, IoTID20) with separate Jupyter notebooks demonstrating batch vs. continual learning workflows.

628 stars. No commits in the last 6 months.