Predicting the forex market with CNN-BiLSTM and CNN-LTSM
Loading...
Supplementary material
Other Title
Authors
Varastehpour, S.
Abdolahi, A.
Modares, A.F.A.
Varastehpour, Soheil
Abdolahi, A.
Modares, A.F.A.
Varastehpour, Soheil
Author ORCID Profiles (clickable)
Degree
Grantor
Date
2025-07
Supervisors
Type
Conference Contribution - Paper in Published Proceedings
Ngā Upoko Tukutuku (Māori subject headings)
Keyword
forex
foreign exchange markets
prediction
Long Short-Term Memory (LSTM)
Convolutional Neural Network (CNN)
Bidirectional Long Short-Term Memory (BiLSTM)
deep-learning algorithms
computer modelling
algorithms
foreign exchange markets
prediction
Long Short-Term Memory (LSTM)
Convolutional Neural Network (CNN)
Bidirectional Long Short-Term Memory (BiLSTM)
deep-learning algorithms
computer modelling
algorithms
ANZSRC Field of Research Code (2020)
Citation
Varastehpour, S., Abdolahi, A., Modares, A. F. A., & Varastehpour, S. (2025). Predicting the forex market with CNN-BiLSTM and CNN-LTSM. In S. Varastehpour & M. Shakiba (Eds.), Proceedings: AIOT Global Summit 2025: Economic Growth, 15–16 July (pp. 100–105). ePress, Unitec. https://doi.org/10.34074/proc.250118
Abstract
The foreign exchange (Forex) market is among the most volatile and complex financial systems. In this study, we examine the effectiveness of advanced deep learning models, including convolutional neural networks (CNN), long short-term memory (LSTM), bidirectional long short-term memory (BiLSTM), and their hybrid combinations for forecasting exchange rates. Historical data from Yahoo Finance (2004–25) at daily intervals was utilised for model training. The aim was to evaluate predictive performance regarding accuracy and risk reduction to support informed financial decision-making by focusing on major currency pairs such as GBP/USD and EUR/GBP. The results demonstrate that the proposed models can predict exchange rates with minimal error.
Publisher
Unitec ePress
Permanent link
Link to ePress publication
DOI
https://doi.org/10.34074/proc.250118
Copyright holder
Authors
Copyright notice
CC BY-NC Attribution-NonCommercial 4.0 International