Stock Market Prediction with Lasso Regression using Technical Analysis and Time Lag

摘要

Stock price prophecy is one of the most recent topics of exploration in both university and business. Stock market is based on psychology of traders and it's uncertain but this uncertainty can be dodged based upon technical analysis. Though real live trading data have a few features but based upon the calculations of these less features more features are created that makes prediction an organized task. In this paper Least Absolute Shrinkage and Selection Operator (LASSO) Regression along with added features based on Technical Analysis such as Moving Averages, Relative Strength Index, Super Trend and Time Lag calculations, a proposed novel method to predict stock prices. The model is able to perform very well in terms of prediction on features that are added considering further days prices as targets. National Stock Exchange (NSE) NIFTY 50 index stock data is taken for empirical calculations.