The University of Southampton
University of Southampton Institutional Repository

Comparing the effectiveness of deep feedforward neural networks and shallow architectures for predicting stock price indices

Comparing the effectiveness of deep feedforward neural networks and shallow architectures for predicting stock price indices
Comparing the effectiveness of deep feedforward neural networks and shallow architectures for predicting stock price indices
Many existing learning algorithms suffer from limited architectural depth and the locality of estimators, making it difficult to generalize from the test set and providing inefficient and biased estimators. Deep architectures have been shown to appropriately learn correlation structures in time series data. This paper compares the effectiveness of a deep feedforward Neural Network (DNN) and shallow architectures (e.g., Support Vector Machine (SVM) and one-layer NN) when predicting a broad cross-section of stock price indices in both developed and emerging markets. An extensive evaluation is undertaken, using daily, hourly, minute and tick level data related to thirty-four financial indices from 32 countries across six years. Our evaluation results show a considerable advantage from training deep (cf. shallow) architectures, using a rectifier linear (RELU) activation function, across all thirty-four markets when ‘minute’ data is used. However, the predictive performance of DNN was not significantly better than that of shallower architectures when using tick level data. This result suggests that when training a DNN algorithm, the predictive accuracy peaks, regardless of training size. We also examine which activation function works best for stock price index data. Our results demonstrate that the RELU activation function performs better than TANH across all markets and time horizons when using DNN to predict stock price indices.
Deep feedforward neural network, Financial time series forecasting, Machine learning, Market efficiency
0957-4174
1-44
Orimoloye, Olanrewaju
9e09fc96-21a8-4106-b347-59c390a61f5f
Sung, Ming-Chien
2114f823-bc7f-4306-a775-67aee413aa03
Ma, Tiejun
1f591849-f17c-4209-9f42-e6587b499bae
Johnson, Johnnie E.V.
6d9f1a51-38a8-4011-a792-bfc82040fac4
Orimoloye, Olanrewaju
9e09fc96-21a8-4106-b347-59c390a61f5f
Sung, Ming-Chien
2114f823-bc7f-4306-a775-67aee413aa03
Ma, Tiejun
1f591849-f17c-4209-9f42-e6587b499bae
Johnson, Johnnie E.V.
6d9f1a51-38a8-4011-a792-bfc82040fac4

Orimoloye, Olanrewaju, Sung, Ming-Chien, Ma, Tiejun and Johnson, Johnnie E.V. (2020) Comparing the effectiveness of deep feedforward neural networks and shallow architectures for predicting stock price indices. Expert Systems with Applications, 139, 1-44, [112828]. (doi:10.1016/j.eswa.2019.112828).

Record type: Article

Abstract

Many existing learning algorithms suffer from limited architectural depth and the locality of estimators, making it difficult to generalize from the test set and providing inefficient and biased estimators. Deep architectures have been shown to appropriately learn correlation structures in time series data. This paper compares the effectiveness of a deep feedforward Neural Network (DNN) and shallow architectures (e.g., Support Vector Machine (SVM) and one-layer NN) when predicting a broad cross-section of stock price indices in both developed and emerging markets. An extensive evaluation is undertaken, using daily, hourly, minute and tick level data related to thirty-four financial indices from 32 countries across six years. Our evaluation results show a considerable advantage from training deep (cf. shallow) architectures, using a rectifier linear (RELU) activation function, across all thirty-four markets when ‘minute’ data is used. However, the predictive performance of DNN was not significantly better than that of shallower architectures when using tick level data. This result suggests that when training a DNN algorithm, the predictive accuracy peaks, regardless of training size. We also examine which activation function works best for stock price index data. Our results demonstrate that the RELU activation function performs better than TANH across all markets and time horizons when using DNN to predict stock price indices.

Text
ESWA-D-19-01131R1_20190719 (005) - Accepted Manuscript
Download (674kB)

More information

Accepted/In Press date: 19 July 2019
e-pub ahead of print date: 23 July 2019
Published date: January 2020
Keywords: Deep feedforward neural network, Financial time series forecasting, Machine learning, Market efficiency

Identifiers

Local EPrints ID: 432578
URI: http://eprints.soton.ac.uk/id/eprint/432578
ISSN: 0957-4174
PURE UUID: cab9f9f3-c2d5-485b-9c51-9d97d9506175
ORCID for Ming-Chien Sung: ORCID iD orcid.org/0000-0002-2278-6185

Catalogue record

Date deposited: 19 Jul 2019 10:04
Last modified: 06 Jun 2024 04:16

Export record

Altmetrics

Contributors

Author: Olanrewaju Orimoloye
Author: Ming-Chien Sung ORCID iD
Author: Tiejun Ma
Author: Johnnie E.V. Johnson

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×