Distributed denial-of-service is still used by attackers today, although it is an old method of cyber attack. Attackers are performing such attacks on various layers using the existing weaknesses of the protocols on the internet. Today, machine learning methods can be applied to high-dimensional data sets together with developing technology. The data sets to be used for the detection of cyber attacks are log files with a high number of rows. In this study, it is aimed to analyze the logs obtained in distributed denial-of-service attacks to build the prediction model. Cyber security data sets are brought into a trainable state using ensemble methods. Model performance measurement was applied using different parameters. It is aimed to create a model with the highest degree of accuracy in this way. The classification performance of the proposed model is shared with tables and figures.