Forex Daily Price Prediction Using Gated Recurrent Unit

Citation

Ong, Jia You and Lim, Kian Ming and Lee, Chin Poo and Lim, Jit Yan (2023) Forex Daily Price Prediction Using Gated Recurrent Unit. In: 2023 IEEE 11th Conference on Systems, Process & Control (ICSPC), 16-16 December 2023, Malacca, Malaysia.

[img] Text
38.pdf - Published Version
Restricted to Repository staff only

Download (1MB)

Abstract

The foreign exchange (Forex) market is globally recognized as one of the most prominent financial markets. In this paper, we focus on three major currency pairs: EUR/USD, GBP/USD, and USD/CHF, spanning from January 2007 to July 2022. We employ a range of techniques, including technical indicators, feature scaling, and Gated Recurrent Unit (GRU) network, to predict the closing price one day ahead of the current day. Our method demonstrates superior performance compared to other state-of-the-art approaches, achieving remarkably low Mean Absolute Errors (MAE) of 0.0046, 0.0063, and 0.0039 for the respective currency pairs: EUR/USD, GBP/USD, and USD/CHF. Keywords— Forex price prediction, Recurrent neural networks, Gated Recurrent Unit

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Forex price prediction, Recurrent neural networks, Gated Recurrent Unit
Subjects: Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science
Divisions: Faculty of Information Science and Technology (FIST)
Depositing User: Ms Nurul Iqtiani Ahmad
Date Deposited: 27 Mar 2024 00:56
Last Modified: 27 Mar 2024 00:57
URII: http://shdl.mmu.edu.my/id/eprint/12197

Downloads

Downloads per month over past year

Loading...
View Item
View Item
Edit (login required)