Publications-Periodical Articles
Article View/Open
Publication Export
-
題名 Application of a Dual‑Stream Hybrid Network for Exchange Rate Prediction 作者 林建秀
Lin, Chien-Hsiu;Chen, Si-Qi;Liao, Szu-Lang貢獻者 金融系 關鍵詞 Exchange rate prediction; Convolutional long short-term memory; Hybrid neural network; Dual-stream architecture 日期 2025-05 上傳時間 2025-11-14 摘要 Exchange rate prediction has consistently been a popular research topic in the financial domain. In 2020, in response to the COVID-19 pandemic, the United States implemented large-scale quantitative easing policies. However, in 2022, to address domestic inflation, the United States began a series of significant interest rate hikes. Under these circumstances, the exchange rates of various currencies have experienced substantial fluctuations. In this study, we propose a novel hybrid model based on the Convolutional Long Short-Term Memory (CNN-LSTM) model, combined with a Residual Network (ResNet), aiming to improve the accuracy of exchange rate predictions. By integrating signal processing techniques such as Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and Savitzky-Golay (SG) filters with an innovative dual-stream (DS) architecture, our model (DS-ResNet-LSTM) demonstrates outstanding performance across multiple metrics, significantly outperforming the traditional LSTM, CNN-LSTM and others. The experimental results indicate that the DS-ResNet-LSTM model exhibits strong robustness, high generalization capability, and clear advantages in numerical prediction, demonstrating its potential in financial time series analysis. 關聯 Computational Economics 資料類型 article DOI https://doi.org/10.1007/s10614-025-10957-6 dc.contributor 金融系 dc.creator (作者) 林建秀 dc.creator (作者) Lin, Chien-Hsiu;Chen, Si-Qi;Liao, Szu-Lang dc.date (日期) 2025-05 dc.date.accessioned 2025-11-14 - dc.date.available 2025-11-14 - dc.date.issued (上傳時間) 2025-11-14 - dc.identifier.uri (URI) https://ah.lib.nccu.edu.tw/item?item_id=179794 - dc.description.abstract (摘要) Exchange rate prediction has consistently been a popular research topic in the financial domain. In 2020, in response to the COVID-19 pandemic, the United States implemented large-scale quantitative easing policies. However, in 2022, to address domestic inflation, the United States began a series of significant interest rate hikes. Under these circumstances, the exchange rates of various currencies have experienced substantial fluctuations. In this study, we propose a novel hybrid model based on the Convolutional Long Short-Term Memory (CNN-LSTM) model, combined with a Residual Network (ResNet), aiming to improve the accuracy of exchange rate predictions. By integrating signal processing techniques such as Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and Savitzky-Golay (SG) filters with an innovative dual-stream (DS) architecture, our model (DS-ResNet-LSTM) demonstrates outstanding performance across multiple metrics, significantly outperforming the traditional LSTM, CNN-LSTM and others. The experimental results indicate that the DS-ResNet-LSTM model exhibits strong robustness, high generalization capability, and clear advantages in numerical prediction, demonstrating its potential in financial time series analysis. dc.format.extent 106 bytes - dc.format.mimetype text/html - dc.relation (關聯) Computational Economics dc.subject (關鍵詞) Exchange rate prediction; Convolutional long short-term memory; Hybrid neural network; Dual-stream architecture dc.title (題名) Application of a Dual‑Stream Hybrid Network for Exchange Rate Prediction dc.type (資料類型) article dc.identifier.doi (DOI) 10.1007/s10614-025-10957-6 dc.doi.uri (DOI) https://doi.org/10.1007/s10614-025-10957-6
