Network Intrusion Detection System using Random Forest and Gradient Boosting Machines

The recent technological advancements not only astonish us but also demonstrates that if they are misapplied, they can pose a serious threat. A Network intrusion Detection system (NIDS) is presented in this paper which leverages the abilities of Random Forest and Extreme gradient boosting Machine (Xgbm) classifiers and harnesses the ensemble of both classifiers which enhances the accuracy of the system and brings out the best in both the classifiers. The system is trained using the UNSWNB15 dataset. Additionally, the system also employs the statistical and Recursive Feature Elimination for feature selection which enhances the model’s performance.