Recent trends have revealed that DDoS attacks contribute to the majority of overall network attacks. Networks face challenges in distinguishing between legitimate and malicious flows. The testing and implementation of DDoS strategies are not easy to deploy due to many factors like complexities, rigidity, cost, and vendor specific architecture of current networking equipment and protocols. Work is being done to detect DDoS attacks by application of Machine Learning (ML) models but to find out the best ML model among the given choices, is still an open question. This work is motivated by two research questions: 1) which supervised learning algorithm will give the best outcomes to detect DDoS attacks. 2) What would be the accuracy of training these algorithms on a real-life dataset? We achieved more than 96% accuracy in the case of Random Forest Classifier and validated our results using two metrics. The outcome was also compared with the other works to confirm its adequacy. We also present a detailed analysis to support our findings.