Nowadays, a major cyber-attack is known as a Distributed Denial of Service (DDoS). It disrupts the legitimate users to access the server or network resources. Server or network resource is unavailable is not a small issue these days, because everything is online. So DDoS attacks detection is the key research area to find the best DDoS attack detection. This study evaluate the Logistic Regression, Naïve Bayes, Decision Tree, KNN, Random Forest, Ada Boost, Gradient Boost, Multi-Layer Perceptron classification algorithms in order to detect SSDP DDoS attack. CIC-DDoS2019 dataset is used in this study. Classification algorithms evaluated for SSDP DDoS attack detection with different uncorrelated features subsets selected by different correlation methods of Pearson, Kendall and Spearman methods. Classification algorithms evaluated by different metrics of accuracy, Log-loss value, ROC-AUC score, K-Fold cross validation accuracy. MLP, KNN classification algorithms gives the best classification results to detect SSDP DDoS attacks.