Publications-Theses
Article View/Open
Publication Export
Google ScholarTM
NCCU Library
Citation Infomation
Related Publications in TAIR
| Title | 納入EFFR與FFF之SOFR利率預測：Vasicek和LSTM模型預測之比較 Forecasting SOFR Rate with EFFR and FFF: Comparison between Vasicek and LSTM Models |
| Creator | 張安慧 Chang, An-Hui |
| Contributor | 胡毓忠<br>林士貴 Hu, Yuh-Jong<br>Lin, Shih-Kuei 張安慧 Chang, An-Hui |
| Key Words | SOFR Vasicek LSTM FOMC 聯邦基金利率期貨 聯邦資金有效利率 SOFR Vasicek LSTM FOMC EFFR FFF |
| Date | 2023 |
| Date Issued | 12-Sep-2023 11:11:49 (UTC+8) |
| Summary | SOFR利率逐步取代USD LIBOR成為主要金融商品訂價參考指標。有鑒於轉換參考利率對於金融市場和實體經濟都會產生重大影響，因此有必要製作一有效且可靠的SOFR利率預測模型。本研究以Vasicek和LSTM模型驗證多變量模型預測利率的優勢。首先，將聯邦基金利率期貨和聯邦資金有效利率分別納入Vasicek和LSTM模型，實證結果指出納入上述兩個因子可以強化模型捕捉貨幣政策變動的能力，減少原本模型在貨幣政策變動後預測值短期內偏離實際值的幅度。此結果亦符合經濟直覺，即模型考量更多有效資訊後表現更佳，此結果在Vasicek和LSTM模型上都得到驗證。其次，利用LSTM模型靈活度高、容易納入更多預測變數之優點，再將總體經濟因子加入已經含有前述提及之聯邦基金利率期貨、聯邦資金有效利率和SOFR歷史資料的LSTM模型之中，發現結合貨幣政策和總體經濟因子以及SOFR歷史資料的LSTM模型，於降息期間預測表現優於僅納入SOFR歷史資料和貨幣政策相關因子的LSTM模型。不過LSTM模型於升息期間納入總體因子後，預測表現之改善幅度並未如同降息期間一般顯著，此結果代表於不同貨幣政策時期，納入總體因子所能減少的模型誤差幅度並不相同。 As USD LIBOR to SOFR transition has started, it is crucial to construct a reliable model for forecasting the SOFR rate. This study justifies the advantages of using a multivariate model to forecast interest rates. Initially, we employ both Vasicek and LSTM models, incorporating the federal funds rate futures and effective federal funds rate as input factors. The empirical results indicate that including these two factors improves the model`s ability to reduce the deviation between predicted and actual values after monetary policy changes. This result aligns with economic intuition, as including more relevant information enhances the model`s performance. Both Vasicek and LSTM models justify the advantages of using a multivariate model. Moreover, the LSTM model performs better after incorporating macroeconomic factors alongside the aforementioned federal funds rate futures, effective federal funds rate, and historical SOFR data, especially during rate-cutting periods. That is, the improvement of performances after incorporating more relevant macroeconomic factors into the LSTM model during rate-hiking periods is less significant than during rate-cutting periods. This result suggests that the reduction in model error achieved by including macroeconomic factors varies depending on the different monetary policy periods. |
| 參考文獻 | Baghestani, H. (2016). Interest rate movements and us consumers’ inflation forecast errors: is there a link? Journal of Economics and Finance, 40(3):623–630. Bauer, M. D. and Rudebusch, G. D. (2020). Interest rates under falling stars. American Economic Review, 110(5):1316- 54. Chen, L. and Xu, M. (2020). Piecewise time series prediction based on stacked long short-term memory and genetic algorithm. In 2020 Chinese Automation Congress (CAC), pages 519–525. CME Group (2023). Understanding the cme group fedwatch tool methodology. Cornelissen, J. (2021). A study on forecasting sofr with a recurrent neural network using long short-term memory cells. Master’s thesis, University of Twente. Cox, J. C., Ingersoll, J. E., and Ross, S. A. (1985). An intertemporal general equilibrium model of asset prices. Econometrica, 53(2):363–384. Duffie, D. and Kan, R. (1996). A yield-factor model of interest rates. Mathematical Finance, 6(4):379–406. Fisher, I. (1930). The Theory of Interest, volume 43, pages 1–19. New York: Macmillan. Fisher, M. and Robertson, B. (2016). Market expectations of fed policy: A new tool. Lim, B. and Zohren, S. (2021). Time-series forecasting with deep learning: a survey. Philosophical Transactions of the Royal Society A, 379(2194):20200209. Pakko, M. R. and Wheelock, D. C. (1996). Monetary policy and financial market expectations: what did they know and when did they know it? Review, 78(Jul):19–32. Sarno, L., Thornton, D., and Valente, G. (2004). Federal funds rate prediction. Working Papers 2002-005, Federal Reserve Bank of St. Louis. Thenmozhi, M. (2006). Forecasting stock index returns using neural networks. Delhi Business Review, 7(2):59–69. Vasicek, O. (1977). An equilibrium characterization of the term structure. Journal of Financial Economics, 5(2):177–188. Verstyuk, S. (2019). Modeling multivariate time series in economics: From auto-regressions to recurrent neural networks. Available at SSRN 3357211. Wang, G. and Hausken, K. (2022). Interest Rates, the Taylor Rule, the Quantity Equation, and the Phillips Curve. Eurasian Journal of Economics and Finance, 10(3):83–93. Zhang, Y., Yan, B., and Aasma, M. (2020). A novel deep learning framework: Prediction and analysis of financial time series using ceemd and lstm. Expert Systems with Applications, 159:113609. |
| Description | 碩士 國立政治大學 國際金融碩士學位學程 111ZB1035 |
| 資料來源 | http://thesis.lib.nccu.edu.tw/record/#G0111ZB1035 |
| Type | thesis |
| dc.contributor.advisor | 胡毓忠<br>林士貴 | zh_TW |
| dc.contributor.advisor | Hu, Yuh-Jong<br>Lin, Shih-Kuei | en_US |
| dc.contributor.author (Authors) | 張安慧 | zh_TW |
| dc.contributor.author (Authors) | Chang, An-Hui | en_US |
| dc.creator (作者) | 張安慧 | zh_TW |
| dc.creator (作者) | Chang, An-Hui | en_US |
| dc.date (日期) | 2023 | en_US |
| dc.date.accessioned | 12-Sep-2023 11:11:49 (UTC+8) | - |
| dc.date.available | 12-Sep-2023 11:11:49 (UTC+8) | - |
| dc.date.issued (上傳時間) | 12-Sep-2023 11:11:49 (UTC+8) | - |
| dc.identifier (Other Identifiers) | G0111ZB1035 | en_US |
| dc.identifier.uri (URI) | http://nccur.lib.nccu.edu.tw/handle/140.119/147556 | - |
| dc.description (描述) | 碩士 | zh_TW |
| dc.description (描述) | 國立政治大學 | zh_TW |
| dc.description (描述) | 國際金融碩士學位學程 | zh_TW |
| dc.description (描述) | 111ZB1035 | zh_TW |
| dc.description.abstract (摘要) | SOFR利率逐步取代USD LIBOR成為主要金融商品訂價參考指標。有鑒於轉換參考利率對於金融市場和實體經濟都會產生重大影響，因此有必要製作一有效且可靠的SOFR利率預測模型。本研究以Vasicek和LSTM模型驗證多變量模型預測利率的優勢。首先，將聯邦基金利率期貨和聯邦資金有效利率分別納入Vasicek和LSTM模型，實證結果指出納入上述兩個因子可以強化模型捕捉貨幣政策變動的能力，減少原本模型在貨幣政策變動後預測值短期內偏離實際值的幅度。此結果亦符合經濟直覺，即模型考量更多有效資訊後表現更佳，此結果在Vasicek和LSTM模型上都得到驗證。其次，利用LSTM模型靈活度高、容易納入更多預測變數之優點，再將總體經濟因子加入已經含有前述提及之聯邦基金利率期貨、聯邦資金有效利率和SOFR歷史資料的LSTM模型之中，發現結合貨幣政策和總體經濟因子以及SOFR歷史資料的LSTM模型，於降息期間預測表現優於僅納入SOFR歷史資料和貨幣政策相關因子的LSTM模型。不過LSTM模型於升息期間納入總體因子後，預測表現之改善幅度並未如同降息期間一般顯著，此結果代表於不同貨幣政策時期，納入總體因子所能減少的模型誤差幅度並不相同。 | zh_TW |
| dc.description.abstract (摘要) | As USD LIBOR to SOFR transition has started, it is crucial to construct a reliable model for forecasting the SOFR rate. This study justifies the advantages of using a multivariate model to forecast interest rates. Initially, we employ both Vasicek and LSTM models, incorporating the federal funds rate futures and effective federal funds rate as input factors. The empirical results indicate that including these two factors improves the model`s ability to reduce the deviation between predicted and actual values after monetary policy changes. This result aligns with economic intuition, as including more relevant information enhances the model`s performance. Both Vasicek and LSTM models justify the advantages of using a multivariate model. Moreover, the LSTM model performs better after incorporating macroeconomic factors alongside the aforementioned federal funds rate futures, effective federal funds rate, and historical SOFR data, especially during rate-cutting periods. That is, the improvement of performances after incorporating more relevant macroeconomic factors into the LSTM model during rate-hiking periods is less significant than during rate-cutting periods. This result suggests that the reduction in model error achieved by including macroeconomic factors varies depending on the different monetary policy periods. | en_US |
| dc.description.tableofcontents | 1 Introduction 1 1.1 Background 1 1.2 Motivation 2 1.3 Research Purposes 4 2 Literature Review 5 2.1 Equilibrium Interest Rate Models 5 2.2 Machine Learning Methods 6 2.3 Policy Rate and FOMC Meeting 8 2.4 Macroeconomic Factors 9 3 Methodologies 11 3.1 Vasicek Model 11 3.2 Long Short-Term Memory (LSTM) Model 12 3.3 Adjustment Term Based on FFF and EFFR 15 4 Empirical Results 18 4.1 Data Source 18 4.2 Descriptive Statistics 19 4.3 Regression Analysis 20 4.4 Model Design 21 4.5 Empirical Results: Vasicek Model and LSTM Model 25 4.5.1 Rate-cut Period 27 4.5.2 Rate-hike Period 28 4.5.3 On-hold Period 29 5 Conclusions and Future Works 30 5.1 Conclusions 30 5.2 Future Works 30 References 32 | zh_TW |
| dc.format.extent | 994645 bytes | - |
| dc.format.mimetype | application/pdf | - |
| dc.source.uri (資料來源) | http://thesis.lib.nccu.edu.tw/record/#G0111ZB1035 | en_US |
| dc.subject (關鍵詞) | SOFR | zh_TW |
| dc.subject (關鍵詞) | Vasicek | zh_TW |
| dc.subject (關鍵詞) | LSTM | zh_TW |
| dc.subject (關鍵詞) | FOMC | zh_TW |
| dc.subject (關鍵詞) | 聯邦基金利率期貨 | zh_TW |
| dc.subject (關鍵詞) | 聯邦資金有效利率 | zh_TW |
| dc.subject (關鍵詞) | SOFR | en_US |
| dc.subject (關鍵詞) | Vasicek | en_US |
| dc.subject (關鍵詞) | LSTM | en_US |
| dc.subject (關鍵詞) | FOMC | en_US |
| dc.subject (關鍵詞) | EFFR | en_US |
| dc.subject (關鍵詞) | FFF | en_US |
| dc.title (題名) | 納入EFFR與FFF之SOFR利率預測：Vasicek和LSTM模型預測之比較 | zh_TW |
| dc.title (題名) | Forecasting SOFR Rate with EFFR and FFF: Comparison between Vasicek and LSTM Models | en_US |
| dc.type (資料類型) | thesis | en_US |
| dc.relation.reference (參考文獻) | Baghestani, H. (2016). Interest rate movements and us consumers’ inflation forecast errors: is there a link? Journal of Economics and Finance, 40(3):623–630. Bauer, M. D. and Rudebusch, G. D. (2020). Interest rates under falling stars. American Economic Review, 110(5):1316- 54. Chen, L. and Xu, M. (2020). Piecewise time series prediction based on stacked long short-term memory and genetic algorithm. In 2020 Chinese Automation Congress (CAC), pages 519–525. CME Group (2023). Understanding the cme group fedwatch tool methodology. Cornelissen, J. (2021). A study on forecasting sofr with a recurrent neural network using long short-term memory cells. Master’s thesis, University of Twente. Cox, J. C., Ingersoll, J. E., and Ross, S. A. (1985). An intertemporal general equilibrium model of asset prices. Econometrica, 53(2):363–384. Duffie, D. and Kan, R. (1996). A yield-factor model of interest rates. Mathematical Finance, 6(4):379–406. Fisher, I. (1930). The Theory of Interest, volume 43, pages 1–19. New York: Macmillan. Fisher, M. and Robertson, B. (2016). Market expectations of fed policy: A new tool. Lim, B. and Zohren, S. (2021). Time-series forecasting with deep learning: a survey. Philosophical Transactions of the Royal Society A, 379(2194):20200209. Pakko, M. R. and Wheelock, D. C. (1996). Monetary policy and financial market expectations: what did they know and when did they know it? Review, 78(Jul):19–32. Sarno, L., Thornton, D., and Valente, G. (2004). Federal funds rate prediction. Working Papers 2002-005, Federal Reserve Bank of St. Louis. Thenmozhi, M. (2006). Forecasting stock index returns using neural networks. Delhi Business Review, 7(2):59–69. Vasicek, O. (1977). An equilibrium characterization of the term structure. Journal of Financial Economics, 5(2):177–188. Verstyuk, S. (2019). Modeling multivariate time series in economics: From auto-regressions to recurrent neural networks. Available at SSRN 3357211. Wang, G. and Hausken, K. (2022). Interest Rates, the Taylor Rule, the Quantity Equation, and the Phillips Curve. Eurasian Journal of Economics and Finance, 10(3):83–93. Zhang, Y., Yan, B., and Aasma, M. (2020). A novel deep learning framework: Prediction and analysis of financial time series using ceemd and lstm. Expert Systems with Applications, 159:113609. | zh_TW |