本研究旨在利用機器學習模型預測美國十年期公債殖利率，選取的變數包括前日債券收盤殖利率（如美國三個月期公債殖利率、美國五年期公債殖利率等）、美國金融指標（如美元指數、S&P500指數等）、美國經濟指標（如首次申請失業救濟金人數、核心個人消費支出指數、實質GDP等）及商品期貨（如黃金現貨價格和WTI西德州原油期貨價格）。
透過比較五種機器學習模型，包括線性迴歸、Lasso、隨機森林、XGBoost和SVR，結果顯示XGBoost在MAE及Accuracy方面表現最佳，隨機森林次之，SVR在高維數據處理能力上表現良好，而線性迴歸及Lasso模型預測性能相對較弱。
結論顯示，XGBoost模型在預測美國十年期公債殖利率方面具有顯著優勢，未來可以考慮進一步優化特徵選擇和模型參數，以提高預測精度。同時，結合更多總體經濟變數和市場情緒指標，將有助於提升模型的解釋能力和應用價值。

　This study aims to predict the yield of US 10-year Treasury bond yields using machine learning models. The selected variables include previous day bond closing yields (e.g., US 3-month Treasury bond yield, US 5-year Treasury bond yield, etc.), US financial indicators (e.g., US Dollar Index, S&P 500 Index, etc.), US economic indicators (e.g., initial jobless claims, core personal consumption expenditures index, real GDP, etc.), and commodity futures (e.g., gold spot price and WTI crude oil futures). By comparing five machine learning models, including Linear Regression, Lasso, Random Forest, XGBoost, and Support Vector Regression (SVR), the results show that the XGBoost model performs the best in terms of MAE and Accuracy, followed by Random Forest. The SVR model demonstrates good performance in handling high-dimensional data, while the Linear Regression model exhibits relatively weaker predictive performance due to its simple assumptions. The conclusion indicates that the XGBoost model has a significant advantage in predicting US 10-year Treasury bond yields. Future research can consider further optimizing feature selection and model parameters to improve prediction accuracy. Additionally, incorporating more macroeconomic variables and market sentiment indicators will enhance the explanatory power and application value of the model.

論文審定書 i
摘　要 ii
Abstract iii
目　錄 iv
圖　次 vi
表　次 vii
第一章 緒論 1
第一節 研究背景 1
第二節 研究動機與目的 3
第三節 研究架構 4
第二章 文獻探討 6
第一節 利率影響因素 6
第二節 債券預測 8
第三節 使用模型 9
第三章 研究方法 13
第一節 資料蒐集 13
第二節 資料預處理 17
第三節 特徵篩選方法 19
第四節 使用模型 22
第五節 研究評估指標 25
第四章 實證分析 28
第一節 輸入特徵 28
第二節 模型參數調整 36
第三節 模型結果 40
第四節 實證綜合結論 51
第五章 結論與建議 52
第一節 研究結論 52
第二節 研究建議 53
參考文獻 54

Alesina, A., & Ardagna, S. (2010). Large changes in fiscal policy: Taxes versus spending. Tax Policy and the Economy, 24(1), 35-68.
Bernanke, B. S., & Gertler, M. (1995). Inside the black box: The credit channel of monetary policy transmission. Journal of Economic Perspectives, 9(4), 27-48.
Bernanke, B. S., & Kuttner, K. N. (2005). What explains the stock market’s reaction to Federal Reserve policy? Journal of Finance, 60(3), 1221-1257.
Bianchi, D., Büchner, M., & Tamoni, A. (2021). Bond risk premiums with machine learning. The Review of Financial Studies, 34(2), 1046-1089.
Borio, C., & Hofmann, B. (2017). Is monetary policy less effective when interest rates are persistently low? BIS Working Papers.
Boudt, K., Carl, P., Peterson, B. G., & Pham, N. (2017). Asset allocation with conditional value-at-risk budgets. The Journal of Risk, 20(1), 79-111.
Box, G. E. P., & Jenkins, G. M. (1970). Time series analysis: Forecasting and control. Holden-Day.
Cao, L., Wang, G., Li, J., & Ye, X. (2019). Financial bond price prediction based on random forest model. Journal of Finance and Data Science, 5(1), 16-27.
Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785-794).
Cochrane, J. H. (2011). Understanding policy in the Great Recession: Some unpleasant fiscal arithmetic. European Economic Review, 55(1), 2-30.
Cox, J. C., Ingersoll, J. E., & Ross, S. A. (1985). A theory of the term structure of interest rates. Econometrica, 53(2), 385-407.
Drucker, H., Burges, C. J. C., Kaufman, L., Smola, A., & Vapnik, V. (1997). Support vector regression machines. In Advances in Neural Information Processing Systems (pp. 155-161).
Frankel, J. A. (1993). On exchange rates. MIT Press.
Goswami, S., Chatterjee, S., & Dey, S. (2018). Forecasting stock prices using decision tree and random forest techniques: A comparative study. International Journal of Computer Science and Information Security (IJCSIS), 16(2).
Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735-1780.
Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., ... & Liu, T. Y. (2017). LightGBM: A highly efficient gradient boosting decision tree. In Advances in Neural Information Processing Systems (pp. 3146-3154).
Leombroni, M., Vedolin, A., Venter, G., & Whelan, P. (2021). Central bank communication and the yield curve. Journal of Financial Economics, 141(3), 860-880.
Mankiw, N. G., & Miron, J. A. (1986). The changing behavior of the term structure of interest rates. Quarterly Journal of Economics, 101(2), 211-228.
Mencía, L., Larsen, K., & Wistuba, M. (2017). Scalable gradient-boosted trees for high-cardinality categorical features. In 2017 IEEE International Conference on Big Data (pp. 1111-1116).
Nelson, C. R., & Siegel, A. F. (1987). Parsimonious modeling of yield curves. Journal of Business, 60(4), 473-489.
Oosterlaken, J. (2020). Predicting the US Treasury Yields using machine learning techniques. Erasmus University Rotterdam, Erasmus School of Economics.
Shu, L., & Chou, J. (2021). Using deep learning techniques to predict 10-year US Treasury yield. 2021 6th International Conference on Inventive Computation Technologies (ICICT), 9440560.
Sims, C. A. (1980). Macroeconomics and reality. Econometrica, 48(1), 1-48.
Sun, X., Chen, T., & Guestrin, C. (2019). Fast and accurate estimation of lattice-based models. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (pp. 357-365).
Swanson, N. R., & Xiong, W. (2018). Big data analytics in economics: What have we learned so far, and where should we go from here? Canadian Journal of Economics/Revue canadienne d'économique, 51(3), 695-746.
Taylor, J. B. (1993). Discretion versus policy rules in practice. Carnegie-Rochester Conference Series on Public Policy, 39, 195-214.
Vayanos, D., Gers, F. A., Schmidhuber, J., & Cummins, F. (1999). Learning to forget: Continual prediction with LSTM (Technical Report IDSIA-01-99). IDSIA.
Yuzvovich, L., Razumovskaya, E., Maramygin, M., Ponkratov, V., Kuznetsov, N., & Bashkirova, N. (2020). Econometric model of the impact of the interest rate on the economic development. Industrial Engineering & Management Systems, 19(1), 254-265.
Zhou, Y., Wang, X., & Sun, X. (2019). Application of support vector machine in forecasting financial bond yields. Journal of Financial Engineering, 6(1), 19-30.
簡嘉瑛（2009）。美國公債殖利率與景氣循環指標間關聯性之探討。國立中央大學財務金融研究所。
陳谷劦（2003）。公債殖利率與總體變數間關係之探討—台灣的實證研究。世新大學經濟學研究所。