Predicting the impact of web based learning amongst undergraduate students helps in reducing and preventing the dropout rates. In this research paper, we have used five different algorithms, mainly Stochastic Gradient Descent (SGD), Support Vector Machines (SVM), K-Nearest Neighbor (KNN), Random Forest Algorithm, Decision tree algorithm. We have done a primary data analysis with 649 data sets from different parts of Mumbai region.SVM classifier is the best algorithm for predicting the impact of web based learning in Mumbai region,with the accuracy of 79.23 followed by SGD Classifier with accuracy of 78.6