The main objective of this paper is to find the best model for predicting the stock market movement. We have tested various models based on machine learning that were previously implemented and during the process, we found out that the Random Forest and Support Vector Machine algorithms were not exploited well. In this paper, we are going to find out a more feasible method to predict the stock market with higher accuracy. We have taken a dataset of stock market prices from previous years and pre-processed the data for real analysis. So, our paper will also be focusing on pre-processing of the raw dataset. After pre-processing, we will be reviewing the use of random forest and support vector machine on the datasets and the outcome it generates. The paper also examines the feasibility of the prediction system in real-world settings and issues associated with the accuracy of predicting the market. If this model achieves higher accuracy than previously implemented machine learning algorithms then it can prove to be a great asset for stockbrokers, institutions, and individual investors.