Enhancement of Neural Networks Model’s Predictions of Currencies Exchange Rates by Phase Space Reconstruction and Harris Hawks’ Optimization

Haider Khan (), Shahryar Ghorbani (), Elham Shabani () and Shahab S. Band ()
Additional contact information
Shahryar Ghorbani: Sakarya University
Elham Shabani: University of Tabriz
Shahab S. Band: National Yunlin University of Science and Technology

Computational Economics, 2024, vol. 63, issue 2, No 13, 835-860

Abstract: Abstract Predictions of variations in exchange rates of other currencies to a vehicle currency such as the Dollar (USD) are vital in order to reduce the risks for international transactions. In this study, we use a heuristic algorithm of Harris Hawks’ optimization (HHO) along with phase space reconstructions (PSRs) coupled to the ANN (PSR-ANNHHO) to predict the daily data of GBP/USD and CAD/USD exchange rates. In this new hybrid model, unlike the previous ones, the input of the model is based on the two parameters of time delay and the embedding dimension. The HHO algorithm increases the performance of ANN, which has can model non-linear systems in a natural manner. The performance of the PSR-ANNHHO model can be compared with the ANN and the ANN hybridized with metaheuristic Algorithm of Innovative Gunner (AIG) model (ANN-AIG). The Modified Diebold–Mariano test indicates the statistical difference between the accuracy of the models. Based on the statistical measures and graphs, the PSR-ANNHHO model predicts exchange rates considerably better than stand-alone ANN and ANN-AIG model in each case. Hence, implementing PSR along with using the heuristic algorithms could increase the accuracy of the model. This model’s precise performance supports the case for it to be employed to predict future exchange rate variations, in order to decrease transactions risks in the global markets.

Keywords: Artificial neural network; Exchange rate; Harris hawks’ optimization; Phase space reconstruction (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10614-023-10361-y Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:kap:compec:v:63:y:2024:i:2:d:10.1007_s10614-023-10361-y

Ordering information: This journal article can be ordered from
http://www.springer. ... ry/journal/10614/PS2

DOI: 10.1007/s10614-023-10361-y

Access Statistics for this article

Computational Economics is currently edited by Hans Amman

More articles in Computational Economics from Springer, Society for Computational Economics Contact information at EDIRC.
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().