Title: A time series analysis-based stock price prediction using machine learning and deep learning models
Authors: Sidra Mehtab; Jaydip Sen
Addresses: School of Computing and Analytics, NSHM Knowledge Campus, 124, B. L. Saha Road, Kolkata – 700053, West Bengal, India ' Department Data Science and Artificial Intelligence, Praxis Business School, Bakrahat Road, Off Diamond Harbor Road, Kolkata 700104, West Bengal, India
Abstract: Prediction of future movement of stock prices has always been a challenging task for researchers. While the advocates of the efficient market hypothesis (EMH) believe that it is impossible to design any predictive framework that can accurately predict the movement of stock prices, there are seminal work in the literature that have demonstrated that time series of a stock price can be predicted with a high level of accuracy. In this paper, we present a very robust and accurate framework of stock price prediction that consists of an agglomeration of statistical, machine learning, and deep learning models. We use daily stock price data, collected at five minutes intervals of time, of a very well-known company that is listed in the National Stock Exchange (NSE) of India. The granular data is aggregated into three slots in a day, and the aggregated data is used for building the forecasting models. Extensive results have been presented on the performance of these models.
Keywords: stock price prediction; time series forecasting; multivariate regression; MARS; random forest; support vector machine; SVM; long- and short-term memory; LSTM; convolutional neural network; CNN; artificial neural networks; ANN; decision trees.
International Journal of Business Forecasting and Marketing Intelligence, 2020 Vol.6 No.4, pp.272 - 335
Received: 21 Apr 2020
Accepted: 04 Dec 2020
Published online: 16 Jun 2021 *