Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

A comparison of SVR and NARX in financial time series forecasting

A comparison of SVR and NARX in financial time series forecasting Machine learning techniques have become attractive due to their robustness and superiority in predicting future behaviour in various areas. This paper is aimed to predict future stock prices by applying a nonlinear autoregressive network with exogenous inputs (NARX) and support vector regression (SVR). For this aim, we use the daily trade data, including highest price, lowest price, closing price, and trade volume for the stocks with the highest transaction volumes from Borsa Istanbul (BIST). In order to evaluate the performance of the prediction models, various statistical measures are used. The experimental results indicate that the techniques used are quite capable of predicting the future price of a stock. Moreover, both methods are competitive with each other and have superiorities in different aspects. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png International Journal of Computational Economics and Econometrics Inderscience Publishers

A comparison of SVR and NARX in financial time series forecasting

Download PDF
18 pages

Loading next page...
 
/lp/inderscience-publishers/a-comparison-of-svr-and-narx-in-financial-time-series-forecasting-IPBAcldtVO
Publisher
Inderscience Publishers
Copyright
Copyright © Inderscience Enterprises Ltd
ISSN
1757-1170
eISSN
1757-1189
DOI
10.1504/ijcee.2022.122835
Publisher site
See Article on Publisher Site

Abstract

Machine learning techniques have become attractive due to their robustness and superiority in predicting future behaviour in various areas. This paper is aimed to predict future stock prices by applying a nonlinear autoregressive network with exogenous inputs (NARX) and support vector regression (SVR). For this aim, we use the daily trade data, including highest price, lowest price, closing price, and trade volume for the stocks with the highest transaction volumes from Borsa Istanbul (BIST). In order to evaluate the performance of the prediction models, various statistical measures are used. The experimental results indicate that the techniques used are quite capable of predicting the future price of a stock. Moreover, both methods are competitive with each other and have superiorities in different aspects.

Journal

International Journal of Computational Economics and Econometrics – Inderscience Publishers

Published: Jan 1, 2022

There are no references for this article.