This book aims to develop a model that classifies whether a certain website is legitimate or malicious using machine learning methodologies and to determine whether increasing a model¿s feature set will lead to an increase in its performance. The authors used three distinct cases to generate an optimal model, each case differs in the number of features used in the dataset. The first case used the base or the original dataset. The second case used an extended feature set. A feature selection algorithm was used in the extended feature set to create a new data set for the third case. The classifiers used to generate the models are Random Forest, J48, C-SVC, and kNN. The result showed an increase in performance when comparing the models of the first case versus the second case. No significant change was observed when the second case¿s models were compared with the third¿s models. The study showed that there is a directly proportional relationship between a model¿s number of features and a model¿s performance. Extending the number of features of the data set leads to an increase in the performance of each model.