Intrusion Detection with Random Forest and XGBoost Architecture: A Soft Voting Approach
With the expansion of the Internet of Things (IoT) and cloud computing networks, the volume and complexity of cyberattacks have increased. Traditional signature-based intrusion detection systems (IDS) are insufficient, especially in unstable datasets and complex attack vectors. In this study, a hybrid ensemble learning model combining Random Forest (RF) and Extreme Gradient Boosting (XGBoost) algorithms is proposed to improve network security. The model makes decisions by weighting the probability scores of the classifiers using a "Soft Voting" mechanism. In experiments conducted on the NSL-KDD dataset, the proposed model achieved a 99.91% accuracy rate, surpassing most current (2024-2025) studies in literature. Furthermore, feature importance analysis is performed to increase the model's transparency, and the 20 most critical features are identified. Finally, the data space is visualized in 3D using the t-SNE algorithm, and it has been observed that the attack classes are separable.