A Stacking Ensemble Learning Framework for Network Intrusion Detection Using XGBoost, LightGBM, CatBoost, and AdaBoost with Random Forest Meta Model

The rise of technology has brought a significant impacts including in cyberthreat. To address these issues, this paper purposes a stacking ensemble framework that combines XGBoost, Catboost, LightGBM, and Adaboost as base model to train data independently in purpose to capture different data pattern and characteristics, a Random Forest meta model is used to enhance detection accuracy and final output. By leveraging the strengths of each individual model and characteristics. The stacking ensemble produces more stable and accurate predictions than any single method. This paper demonstrates the potential of stacking ensemble learning as a robust approach for the needs of future generations.