Among the different types of attacks in the field of Information Technology, DDOS attacks are one of the biggest threats to internet sites and pose a devastating risk to the security of computer systems, mainly due to their potential impact. Hence why research in this area is growing rapidly, with researchers focusing on new ways to address intrusion detection and prevention. Machine learning and Artificial Intelligence are some of the latest additions to the list of technologies studied to perform intrusion detection classification. This study explores the behavior and application of DDoS datasets for machine learning in the context of intrusion detection. The flow in this study, first is to collect raw DDoS datasets from reputable sources. After the data is obtained, the final data set is created for modeling. Data management involves data cleansing, data type transformation and data exchange on data collection. The selection process is accompanied by a model. Two separate algorithms, random and adaboost, are used to train a model with a dataset. The model is validated and retrained with a k-fold cross. The model was eventually evaluated using invisible data. The result is determined by various output sizes. In the experiment, DDoS datasets were used: CICDDoS_2019 The intrusion detection performance of this dataset was analyzed using two machine learning models. The dataset is divided in an 80:20 ratio for model training, validation and testing. Machine learning models are selected systematically and carefully to ensure that experiments are conducted in the right way. The results were analyzed using a set of performance metrics, including accuracy, precision, recall, f-measure, and compute time