Feature enhancement-based stock prediction strategy to forecast the fiscal market

According to consensus, the stock market can be viewed as a complex nonlinear dynamic system influenced by numerous factors. Traditional stock market research and forecasting techniques do not correctly disclose the fundamental pattern of the stock market. Researchers have lately applied a range of machine learning techniques to estimate future stock market values with greater accuracy and precision. The literature indicates that researchers have not been interested in feature engineering for stock price prediction. Consequently, the purpose of this work is to present a unique technique to feature engineering for predicting stock values using historical data. So far we have used the ITC stock for our practical experiment purposes. More importantly, the addition of feature engineering techniques to identify the potential features may improve the accuracy of the forecasted model. We have developed eight forecasted models for comparison purposes and found a simple machine learning algorithm even works well when we provide appropriate features for training the model.