Forecast USD/RMB Exchange Rate and Fitting Comparison Based on Three Methods

Sitong Song

2025

Abstract

In light of the current complex and volatile international landscape, continuously updated exchange rate forecasts are indispensable. Accurate exchange rate forecasts enable enterprises to mitigate trade risks and optimize investment decisions, assist financial institutions in risk management, and support policy formulation. Furthermore, they provide robust support for macroeconomic policymakers, helping to maintain exchange rate stability, balance international payments, and foster steady economic growth, which holds significant importance across all economic levels. In this paper, through Auto-Regressive Integrated Moving Average Model (ARIMA), Error-Trend-Seasonal (ETS) and Simple Moving Average (SMA) traditional time series models forecast the next 10 steps (one step every five consecutive working days) based on the USD/RMB exchange rate in 2022-2025. The result is compared with the actual value pair. In this study, the Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC) are employed for model selection when utilizing ARIMA, ETS, and SMA models. The model's performance was assessed using Root Mean Squared Error (RMSE) and residual P-values. Given the volatile international situation, updated exchange rate forecasts are needed. Accurate exchange rate forecasts enable enterprises to mitigate trade risks and optimize investment decisions, assist financial institutions in risk management, and support policy formulation.

Paper Citation

in Harvard Style

Song S. (2025). Forecast USD/RMB Exchange Rate and Fitting Comparison Based on Three Methods. In Proceedings of the 2nd International Conference on Data Science and Engineering - Volume 1: ICDSE; ISBN 978-989-758-765-8, SciTePress, pages 379-384. DOI: 10.5220/0013697800004670

in Bibtex Style

@conference{icdse25,
author={Sitong Song},
title={Forecast USD/RMB Exchange Rate and Fitting Comparison Based on Three Methods},
booktitle={Proceedings of the 2nd International Conference on Data Science and Engineering - Volume 1: ICDSE},
year={2025},
pages={379-384},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013697800004670},
isbn={978-989-758-765-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 2nd International Conference on Data Science and Engineering - Volume 1: ICDSE
TI - Forecast USD/RMB Exchange Rate and Fitting Comparison Based on Three Methods
SN - 978-989-758-765-8
AU - Song S.
PY - 2025
SP - 379
EP - 384
DO - 10.5220/0013697800004670
PB - SciTePress