Stock Market Analytics: Statistical and Machine Learning Techniques

Stock Prices tend to be erratic in behavior. They can be very volatile in nature, making it hard to predict. Thus, making an accurate analysis is beyond casual means. One method we use is to study historic data and learn patterns of uptrend and down- trend. Standard deviation is calculated on stock prices within a duration of quarter or a year under the close to close measure method. Many other statistical methods have been reviewed and analyzed. In this Project the efficiency of machine learning techniques including Random Forest (RF), Gradient Boosting (GB), Linear Regression (LR), and Decision Tree (DT) are proposed to be implemented and analyzed. This project aims to identify the most efficient Machine Learning Algorithm for consistent stock market analysis.