Combining deep learning and multiresolution analysis for stock market forecasting

Khaled A. Althelaya, Salahadin A. Mohammed*, El Sayed M. El-Alfy

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

23 Scopus citations

Abstract

Due to its complexity, financial time-series forecasting is regarded as one of the most challenging problems. During the past two decades, nonlinear modeling techniques, such as artificial neural networks, were commonly employed to solve a variety of time-series problems. Recently, however, deep neural network has been found to be more efficient than those in many application domains. In this article, we propose a model based on deep neural networks that improves the forecasting of stock prices. We investigate the impact of combining deep learning techniques with multiresolution analysis to improve the forecasting accuracy. Our proposed model is based on an empirical wavelet transform which is shown to outperform traditional stationary wavelet transform in capturing price fluctuations at different time scales. The proposed model is demonstrated to be substantially more effective than other models when evaluated on the SP500 stock index and Mackey-Glass time series.

Original languageEnglish
Article number9324831
Pages (from-to)13099-13111
Number of pages13
JournalIEEE Access
Volume9
DOIs
StatePublished - 2021

Bibliographical note

Publisher Copyright:
© 2013 IEEE.

Keywords

  • Deep learning
  • financial time series
  • forecasting
  • long-short term memory
  • multiresolution analysis

ASJC Scopus subject areas

  • General Computer Science
  • General Materials Science
  • General Engineering

Fingerprint

Dive into the research topics of 'Combining deep learning and multiresolution analysis for stock market forecasting'. Together they form a unique fingerprint.

Cite this