Internet surfing has become a vital part of our daily life. So to catch the attention of the users’ different browser vendors compete to set up the new functionality and advanced features that become the source of attacks for the intruder and the websites are put at hazard. The existing approaches are not adequate to protect the surfers which require an expeditious and precise model that can be able to distinguish between the benign or malicious webpages. The design a new classification system to analyze and detect the malicious web pages based on begin or malicious prediction by using machine learning classifiers such as, random forest, support vector machine, naïve Bayes, logistic regression and Random Forest classifiers are trained to predict the malicious web pages based on benign or malicious of the system. This research should be relevant to cyber security professionals and academic researchers as it could form the basis for real-life detection systems or further research work.