DEEP LEARNING AND MACHINE LEARNING MODELS TO FORECAST BSE AND NIFTY SENSEX IT INDEX

Abstract

The primary objective of this work is to build an appropriate mathematical model that helps predict the direction of stock market indices. The stock market is volatile and dynamic, and prediction of its movement will help investors make more optimal strategies and boost their profit. In this context, the data was collected from two major IT indices of India, the BSE IT Index and the NIFTY IT Index. In modeling the time series, autoregressive integrated moving average (ARIMA) was used initially, followed by various machine learning models, like artificial neural network (ANN), recurrent neural network (RNN), and convolutional neural network (CNN). The data analysis exhibited superior performance of ANN models compared to other models for performance criteria such as root mean squared error (RMSE) and mean absolute percentage error (MAPE). This exploratory analysis concluded that ANN models outperform other predicting models to greater accuracy, augmenting previous literature on stock market analysis. This machine learning approach would help investors design optimal strategies and boost their profits in the world of stock market.