Yi, Tor Shin and Md Yusof, Zahayu and Sapiri, Hasimah and Misiran, Masnita (2025) Comparative Performance Analysis in Exchange Rate Prediction: The Case Study of MYR/USD. International Business Education Journal (IBEJ), 18 (1). pp. 153-179. ISSN 1985-2126

Preview

PDF - Published Version Available under License Attribution 4.0 International (CC BY 4.0). Download (470kB) | Preview

Abstract

Prediction of currency exchange rates became highly desirable due to its significant role in financial and managerial decision-making processes. The fluctuations in exchange rate affect the economy of a country. Hence, over the years, various statistical models, along with machine learning techniques, were developed to predict the currency exchange rates of different countries with varying parameters. In this paper, we compared the performance of classical forecasting methods with machine learning approaches in the specific context of exchange rate prediction, focusing on the currency pair MYR/USD. A thorough and careful analysis of experimental results was conducted on the models selected for both classical and machine learning methods, which included Holt’s Linear Exponential Smoothing, ARIMA, and Neural Networks. Additionally, several performance measures such as RMSE, MAPE, and MAE were used to evaluate the forecast accuracy of these models. Our study revealed that Holt’s Linear Exponential Smoothing model exhibited the highest forecasting accuracy compared to ANN and ARIMA models in terms of MAPE and MAE. Conversely, ANN provided the smallest RMSE value, followed by both traditional methods, which yielded the same RMSE value for the series. It is recommended that future studies investigate the incorporation of new methodologies, including the development of a hybrid neural network model, in order to achieve more precise outcomes while tackling social or economic problems.

Item Type:	Article
Uncontrolled Keywords:	Exchange Rate, Artificial Neural Network, Prediction
Subjects:	H Social Sciences > HC Economic History and Conditions
Divisions:	School of Quantitative Sciences
Depositing User:	Mdm. Rozana Zakaria
Date Deposited:	10 Nov 2026 08:42
Last Modified:	10 Nov 2026 08:42
URI:	https://repo.uum.edu.my/id/eprint/34554

Actions (login required)

View Item