This research aims to address the pressing issue of detecting and mitigating distributed denial of service (DDoS) attacks on computer networks. A hybrid machine learning model is proposed that leverages unsupervised and supervised algorithms to classify network traffic as normal or malicious with high accuracy. The CICDDoS2019 dataset containing real and simulated attack traffic is used to train and evaluate various classification algorithms. Feature selection is applied to extract the most relevant attributes for detection. The proposed ensemble model combines K-Means clustering, random forest, extreme gradient boosting, adaptive boosting, support vector machine, and artificial neural network classifiers. Experimental results demonstrate the model achieves 99.65% overall accuracy in distinguishing DDoS attacks, outperforming individual algorithms. This research contributes towards developing more robust techniques for analyzing network behaviors and enhancing intrusion detection capabilities.