Cloud computing is an over-the-internet delivery of data storage and computer services. Companies and customers are counting on the delivery and security of their cloud environments. Distributed Denial of Service attacks in the Cloud Computing environment are a common type of threat. This threat will only increase in number as cloud computing is adopted more in the future. Machine learning detection methods are popular in the cloud environment for DDoS detection. Various algorithms and datasets are used when training and classifying DDoS attacks. This paper will look at two commonly used classifier algorithms and compare them using accuracy, precision, and recall. These algorithms will be evaluated on three different benchmark datasets. The datasets used for efficiency evaluation are NSL-KDD, KDD CUP99, and CICIDS 2017. These tests are performed in a binary form meaning the algorithms are predicting neither normal or attack. The results of these commonly used classifiers will be used to determine which is better in terms of accuracy, precision, and recall When predicting on the binary classification of three popular datasets. As well as determining which data set the classifiers worked the best testing on. Some notable results we found. Random Forest was able to achieve 0.99 in all three categories on two of the datasets, KDD-99, and CICDIS2017. NB was slightly worse but still managed to achieve 0.98 or higher in all three metrics on the KDD-99 dataset.