本研究旨在探討石材產業於國際供應鏈運作中，如何在美國關稅政策與匯率波動加劇的環境下，運用遠期避險策略有效降低財務風險。石材產業高度依賴國際原料進口，且原料具高重量、高運輸成本與高單價等特性，使其對匯率變動及關稅調整之敏感度高於一般產業。當前美元、人民幣與新台幣等多幣別結算方式，使企業在面對匯率劇烈變動與國際貿易政策變動時承受更高的採購成本不確定性。此類財務風險不僅侵蝕企業獲利，也影響供應鏈運作的連續性與韌性，突顯建構有效風險管理架構的重要性。
傳統避險策略(如逢低買匯或固定比例避險)多依賴經驗法則，較難因應匯率市場跳躍性與非線性的變動特徵。本研究基於此限制，建構一套整合性分析架構，結合「多元迴歸分析」與「機器學習隨機森林演算法」，以量化美國對等關稅與匯率波動對石材採購成本的影響，並預測未來三個月匯率走勢。研究結果顯示，隨機森林模型在處理高維度、多變量與非線性市場結構方面具有優勢，其預測效能明顯優於傳統統計模型。
基於實證結果，本研究提出創新之「動態雙層避險策略」：第一層以匯率預測結果為基礎，動態調整遠期避險的啟動時機與避險比例；第二層將關稅衝擊納入供應鏈決策，使企業得以同步提升採購彈性與供應鏈韌性。模擬分析結果顯示，相較於固定比例避險策略，本研究提出的方法可降低約 18.5% 之成本變異性，顯示其具備高度的實務應用價值。
本研究最終提出一套兼具理論意涵與實務可行性的匯率與關稅風險管理架構，期能協助石材業者在複雜多變的國際貿易環境中強化決策品質，提升供應鏈穩定性與企業競爭力。

This study investigates how firms in the stone industry can mitigate financial risk and enhance supply chain resilience through the application of forward hedging strategies under conditions of intensified tariff policies and exchange rate volatility. The stone industry is characterized by heavy reliance on imported raw materials, high transportation costs, and high unit values, which make procurement costs highly sensitive to fluctuations in exchange rates and trade policies. The coexistence of multiple settlement currencies—primarily the U.S. dollar (USD), Chinese yuan (CNY), and New Taiwan dollar (TWD)—further amplifies cost uncertainty in international procurement.
Traditional hedging approaches, such as fixed-ratio hedging or opportunistic foreign currency purchases, often rely on managerial experience and lack the ability to respond effectively to nonlinear and abrupt market movements. To address these limitations, this study develops an integrated analytical framework that combines multiple regression analysis with a machine learning–based random forest model to quantify the impact of exchange rate movements and tariff factors on procurement costs and to forecast short-term exchange rate trends.
Based on empirical results, this study proposes a Dynamic Dual-Layer Hedging Strategy. The first layer dynamically adjusts the timing and scale of forward hedging based on exchange rate forecasts, while the second layer incorporates tariff-related risks into supply chain decision-making. Simulation results demonstrate that the proposed strategy reduces cost variability by approximately 18.5% compared with conventional fixed hedging approaches, indicating strong practical applicability. Overall, this study contributes a decision-oriented risk management framework that enhances cost stability and supply chain resilience in the global stone industry.

1.Badhan, I. A., Neeroj, M. H., & Rahman, S. (2024). Currency rate fluctuations and their impact on supply chain risk management: An empirical analysis. International journal of business and management sciences, 4(10), 6-26.
2.Breiman, L. (2001). Random forests. Machine learning, 45(1), 5-32.
3.Fan, D., Zhou, Y., Yeung, A. C., Lo, C. K., & Tang, C. (2022). Impact of the US–China trade war on the operating performance of US firms: The role of outsourcing and supply base complexity. Journal of Operations Management, 68(8), 928-962.
4.Gurtu, A., & Johny, J. (2021). Supply chain risk management: Literature review. Risks, 9(1), 16.
5.Hall, T. (2003). Controlling for risk: An analysis of China's system of foreign exchange and exchange rate management. Colum. J. Asian L., 17, 433.
6.Ho, W., Zheng, T., Yildiz, H., & Talluri, S. (2015). Supply chain risk management: a literature review. International journal of production research, 53(16), 5031-5069.
7.Jin, T. (2024, October). Integrated machine learning for enhanced supply chain risk prediction. In Proceedings of the 2024 8th International Conference on Electronic Information Technology and Computer Engineering (pp. 1254-1259).
8.Li, S. T., Chiu, K. C., & Chiu, T. H. (2020, December). An application on building information model to procurement strategy of copper raw material with big data analytics. In 2020 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM) (pp. 696-700). IEEE.
9.Pellegrino, R., Gaudenzi, B., & Zsidisin, G. A. (2024). Mitigating foreign exchange risk exposure with supply chain flexibility: A real option analysis. Journal of Business Logistics, 45(1), e12338.
10.Pournader, M., Kach, A., & Talluri, S. (2020). A review of the existing and emerging topics in the supply chain risk management literature. Decision sciences, 51(4), 867-919.
11.Powers, W., & Schreiber, S. (2023). Measuring the Impact of Trade Cost Volatility on Supply Chains: An Application to Plastics and Light Truck Manufacturing. US International Trade Commission.
12.Settembre-Blundo, D., González-Sánchez, R., Medina-Salgado, S., & García-Muiña, F. E. (2021). Flexibility and resilience in corporate decision making: a new sustainability-based risk management system in uncertain times. Global Journal of Flexible Systems Management, 22(Suppl 2), 107-132.
13.Udenio Castro, M., Zhang, J., & Dabadghao, S. (2024). Global sourcing under tariffs: A perspective of time series analysis. International Journal Of Production Economics, 280.
14.Zai, F. S., & Mansur, A. (2024). Hedging Strategy to Mitigate Exchange Rate Risk in Cross-Border Transactions: Literature Review. Journal of Business Management and Economic Development, 2(03), 1155-1168.
1.世界貿易組織(2024)。2024 年世界貿易報告：經濟韌性與全球貿易。取自 https://www.wto.org/ (檢索日期：2025年10月15日)。
2.林純央、張窈菱、林嬋娟(2019)，國泰人壽外匯價格變動準備金制度之意涵:匯率風險、避險成本與損益平穩，管理評論，38(1)，頁25-26。
3.經濟部國際貿易署(2025)，7月31日對等關稅調整公告，經濟部。取自：https://www.trade.gov.tw/。
4.財政部關務署(2025)，預報貨物通關報關手冊。取自：https://web.customs.gov.tw/multiplehtml/c52d36ff0f234b0c9a2c9d2c4ae8e3a3
5.經濟部國際貿易署(2024)，國際貿易實務手冊(第二版)。臺北市：經濟部
6.聯合國統計司(2025)。UN Comtrade資料庫。取自 https://comtradeplus.un.org/ (檢索日期：2025年10月15日)。