Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal International Journal Artificial Intelligent and Informatics
Mostafa, Sanoun
Unknown Affiliation
Computer Science & IT Economics, Econometrics & Finance

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Comparison of CNN, CNN-GRU, and GRU Models for Prediction of Hryvnia (Ukraine) Exchange Rate against US Dollar Mostafa, Sanoun
International Journal Artificial Intelligent and Informatics Vol 3, No 2 (2025)
Publisher : Research and Social Study Institute (ReSSI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (353.381 KB) | DOI: 10.33292/ijarlit.v3i2.49

Abstract

This study aims to compare the performance of three neural network-based machine learning models, namely Convolutional Neural Network (CNN), hybrid CNN-Gated Recurrent Unit (CNN-GRU), and Gated Recurrent Unit (GRU) in predicting the exchange rate of the Ukrainian Hryvnia against the United States Dollar. The data used is sourced from Yahoo Finance in the range of 2018 to 2023. The evaluation results show that the CNN-GRU hybrid model provides the best performance with the highest test accuracy of 99.69% and an R² value of 0.6899. The CNN model achieved 98.99% test accuracy but with a negative R² (-1.0343), while the GRU model showed 97.94% test accuracy with a very low R² (-6.3755). This study reveals the advantages of the hybridization approach in modeling financial time series data by combining the feature extraction capabilities of CNN and the sequential modeling capabilities of GRU. These results provide important insights for the development of predictive models for volatile currency markets, especially for emerging economies such as Ukraine.
Co-Authors