One of the most dangerous attacks that is increasing day by day is the distributed denial of service (DDoS) attack. Therefore, it is necessary to develop a model to detect and predict these attacks. To this end, a model was created to detect and prevent DDoS. This model begins by using the distributed DDoS database available on the internet. The next step is data preprocessing to obtain high-quality data. Then, a neural network algorithm is applied to detect DDoS. In the final step, infected data is predicted by taking the infected data that was classified in the previous step and then applying a K-means clustering algorithm. The results obtained with this model yielded an accuracy of 0.99% with a neural network algorithm. The prediction values obtained with the hierarchical clustering algorithm were as follows: {C0: 11748, C1: 9349, C3:4571}.