Forecasting Stock Market Using Regression Models

Many people do not have the resources, knowledge, education, or experience to make solid decisions on investments. The values of companies, financial products, indexes, and their markets regularly fluctuate, some more than others. Discovering patterns may help in developing a model that can predict these changes and provide information for the average investor to evaluate whether it is a good time to invest or not. The objectives of this paper are to use machine learning and statistical techniques to analyze historical financial data, identify measurable targets, discover patterns and correlations, develop machine learning models that can make predictions and evaluate the suitability of these models as a tool to decide whether to invest in specific stocks or not. The Random Forest Regression model seems to be the model of choice as it showed best accuracy and does not overfit the data.