學術產出-Theses
Article View/Open
Publication Export
-
題名 聯準會會議記要的文字分析
Text Mining on FOMC Minutes作者 郭育丞
Kuo, Yu-Cheng貢獻者 余清祥
Yue, Ching-Syang
郭育丞
Kuo, Yu-Cheng關鍵詞 文字分析
聯準會會議紀要
寫作風格
探索式資料分析
維度縮減
Text mining
FOMC minutes
Writing style
Exploratory data analysis
Dimension reduction日期 2021 上傳時間 2-Sep-2021 18:18:40 (UTC+8) 摘要 本文探討聯邦公開市場委員會（Federal Open Market Committee，簡稱 FOMC）會議紀要（minutes）的文字風格，尋找不同的利率調整結果（升息、降息、利率不變）時的 FOMC會議紀要的用詞有哪些差異。本文研究資料為1993～2020年的FOMC會議紀要，以及同時期的目標聯邦基金利率（targeted federal funds rate）。透過探索式資料分析（exploratory data analysis）、文字分析（或稱文字探勘）的技術，比較FOMC會議紀要在升息、降息、利率不變時的會議紀要風格。分析發現，目標聯邦基金利率的調整並非隨機（亦即具有自相關性），經常出現連續幾期的升息、降息；文字使用，在不同利率調整時有不少差異，其中升息、降息的報告大多強調美國四大族裔的失業率。另外，由於分析會議紀要的原始文檔為高維度的文檔-詞頻矩陣（document-term matrix），考量多達 4102 個變數，除了具有稀疏矩陣（sparse matrix）的特質外，變數過多也會影響資料分析的效率。因此本文使用倍數指標篩選器、線性降維、非線性降維等方法，透過縮減特徵空間維度以提高執行效率，研究發現倍率指標的為度縮減效果最佳，配合羅吉斯迴歸得出之三分類準確率最高。
In this study, our goal is to explore the writing style of FOMC (Federal Open Market Committee) minutes. In particular, we want to know if the style of minutes shows significant differences when the FOMC decided to raise, lower, or hold interest rates. We applied exploratory data analysis and text mining techniques to the FOMC 1993~2020. We found that the adjustments of targeted federal funds rates are not randomly distributed and they show signs of correlation. For example, among the 39 times of raising interest rate, there was one 17 consecutive intertest increase. Also, the minutes tend to emphasis on the unemployment of four major ethnicities when FOMC decided to raise or lower interest rates. On the other hand, there are 4102 variables involved in exploring the writing study of FOMC minutes. This means that the document-term matrix is a sparse matrix and high dimensionality requires a lot of computation time. Thus, adopted dimensionality reduction techniques: multiplication index, linear reduction and non-linear reduction methods. We found that the multiplication index has the best performance and, together with logistic regression, it has the highest accuracy in classifying the writing style of FOMC minutes in the cases of raising, lowering and holding interest rates.參考文獻 一、中文文獻柏南克（2013）。《柏南克的四堂課：聯準會與金融危機》。臺北：財信。孫亮、黃倩（2017）。《實用機器學習》。北京：人民電郵。黃于珊（2017）。「文字探勘在總體經濟上之應用—以美國聯準會會議紀錄為例」，政治大學金融學系碩士論文。二、英文文獻Abel, A. B., Bernanke, B., Croushore, D. (2013). Macroeconomics (8nd ed.). New Jersey, NJ: Pearson.Aggarwal, C. C. (2018). Machine Learning for Text. Cham, CH: Springer International Publishing. https://doi.org/10.1007/978-3-319-73531-3Bernanke, B. (2012). “The Federal Reserve and the Financial Crisis: The Aftermath of the Crisis, Lecture 4.” George Washington University School of Business.https://www.federalreserve.gov/mediacenter/files/chairman-bernanke-lecture4-20120329.pdfBlinder, A. S., Ehrmann, M., de Haan, J., Fratzscher, M., & Jansen, D.-J. (2008). “Central bank communication and monetary policy: A survey of theory and evidence,” Journal of Economic Literature, 46, 910–945. https://doi.org/10.1257/jel.46.4.910Board of Governors of the Federal Reserve System. (2021, January 14). “Federal Open Market Committee: Transcripts and other historical materials.” Board of Governors of the Federal Reserve System. https://www.federalreserve.gov/monetarypolicy/fomc_historical.htmBoukus, E., & Rosenberg, J. V. (2006). “The information content of FOMC minutes.” Federal Reserve Bank of New York. https://doi.org/10.2139/ssrn.922312Cannon, S. (2015). “Sentiment of the FOMC: Unscripted,” Economic Review [Federal Reserve Bank of Kansas City], Fall 2015, pp. 55.Chollet, F. (2018). Deep learning with Python. Shelter Island, NY: Manning Publications.Doh, T., Song, D., & Yang, S. K. (2020). “Deciphering Federal Reserve Communication via Text Analysis of Alternative FOMC Statements.” Federal Reserve Bank of Kansas City, Research Working Paper no. 20-14, October. https://doi.org/10.18651/RWP2020-14Ericsson, N. R. (2016). “Eliciting GDP forecasts from the FOMC’s minutes around the financial crisis,” International Journal of Forecasting, 32, 571–583. https://doi.org/10.1016/j.ijforecast.2015.09.007Ganegedara, T. (2018). Natural Language Processing with TensorFlow. Birmingham, UK: Packt Publishing.Hayoa, B., & Neuenkirch, M. (2013). “Do Federal Reserve Presidents Communicate with a Regional Bias?” Journal of Macroeconomics, 35(4), 62–72. https://doi.org/10.1016/j.jmacro.2012.10.002Huang, Y. L., & Kuan, C. M. (2021). “Economic Prediction with the FOMC Minutes: An Application of Text Mining,” International Review of Economics & Finance, 71, 751-761. https://doi.org/10.1016/j.iref.2020.09.020Hyndman, R. J., & Athanasopoulos, G. (2018). Forecasting: principles and practice (2nd ed.). Melbourne, AU: OTexts. https://otexts.com/fpp2/Joshi, P. (2016). Python Machine Learning Cookbook. Birmingham, UK: Packt Publishing.Jubinskia, D., & Tomljanovich, M. (2013). “Do FOMC Minutes Matter to Markets? An Intraday Analysis of FOMC Minutes Releases on Individual Equity Volatility and Returns,” Review of Financial Economics, 22(3), 86–97. https://doi.org/10.1016/j.rfe.2013.01.002Kliesen, K. L., Levine, B., & Waller, C. J. (2019). “Gauging Market Responses to Monetary Policy Communication,” Federal Reserve Bank of St. Louis Review, pp. 69-91.https://doi.org/10.20955/r.101.69-91Lucca, D. O., & Trebbi F. (2009). “Measuring Central Bank Communication: An Automated Approach with Application to FOMC Statements.” NBER Working Paper, No. 15367. https://doi.org/10.2139/ssrn.1470443Mikolov, T., Sutskever, I., Chen, K., Corrado, G. and Dean, J. (2013). “Distributed Representations of Words and Phrases and their Compositionality.” Proceedings of the 26th International Conference on Neural Information Processing Systems, NIPS’13, Curran Associates, Red Hook, NY, Vol. 2, pp. 3111-3119.Rosa, C. (2013). “The Financial Market Effect of FOMC Minutes,” FRBNY Economic Policy Review, 19(2), 67–81. https://ssrn.com/abstract=2378398Sarkar, D. (2019). Text Analytics with Python (2nd ed.). Bangalore, India: Apress.Shapiro, A.H., & Wilson, D.J. (2019). “Taking the Fed at its Word: A New Approach to Estimating Central Bank Objectives using Text Analysis.” Federal Reserve Bank of San Francisco Working Paper 2019-02. https://doi.org/10.24148/wp2019-02Stekler, H., & Symington, H. (2016). “Evaluating qualitative forecasts: The FOMC minutes, 2006–2010,” International Journal of Forecasting, 32, 559–570.https://doi.org/10.1016/j.ijforecast.2015.02.003VanderPlas, J. (2017). Python Data Science Handbook. California, CA: O’Reilly Media. 描述 碩士
國立政治大學
企業管理研究所(MBA學位學程)
107363015資料來源 http://thesis.lib.nccu.edu.tw/record/#G0107363015 資料類型 thesis dc.contributor.advisor 余清祥 zh_TW dc.contributor.advisor Yue, Ching-Syang en_US dc.contributor.author (Authors) 郭育丞 zh_TW dc.contributor.author (Authors) Kuo, Yu-Cheng en_US dc.creator (作者) 郭育丞 zh_TW dc.creator (作者) Kuo, Yu-Cheng en_US dc.date (日期) 2021 en_US dc.date.accessioned 2-Sep-2021 18:18:40 (UTC+8) - dc.date.available 2-Sep-2021 18:18:40 (UTC+8) - dc.date.issued (上傳時間) 2-Sep-2021 18:18:40 (UTC+8) - dc.identifier (Other Identifiers) G0107363015 en_US dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/137170 - dc.description (描述) 碩士 zh_TW dc.description (描述) 國立政治大學 zh_TW dc.description (描述) 企業管理研究所(MBA學位學程) zh_TW dc.description (描述) 107363015 zh_TW dc.description.abstract (摘要) 本文探討聯邦公開市場委員會（Federal Open Market Committee，簡稱 FOMC）會議紀要（minutes）的文字風格，尋找不同的利率調整結果（升息、降息、利率不變）時的 FOMC會議紀要的用詞有哪些差異。本文研究資料為1993～2020年的FOMC會議紀要，以及同時期的目標聯邦基金利率（targeted federal funds rate）。透過探索式資料分析（exploratory data analysis）、文字分析（或稱文字探勘）的技術，比較FOMC會議紀要在升息、降息、利率不變時的會議紀要風格。分析發現，目標聯邦基金利率的調整並非隨機（亦即具有自相關性），經常出現連續幾期的升息、降息；文字使用，在不同利率調整時有不少差異，其中升息、降息的報告大多強調美國四大族裔的失業率。另外，由於分析會議紀要的原始文檔為高維度的文檔-詞頻矩陣（document-term matrix），考量多達 4102 個變數，除了具有稀疏矩陣（sparse matrix）的特質外，變數過多也會影響資料分析的效率。因此本文使用倍數指標篩選器、線性降維、非線性降維等方法，透過縮減特徵空間維度以提高執行效率，研究發現倍率指標的為度縮減效果最佳，配合羅吉斯迴歸得出之三分類準確率最高。 zh_TW dc.description.abstract (摘要) In this study, our goal is to explore the writing style of FOMC (Federal Open Market Committee) minutes. In particular, we want to know if the style of minutes shows significant differences when the FOMC decided to raise, lower, or hold interest rates. We applied exploratory data analysis and text mining techniques to the FOMC 1993~2020. We found that the adjustments of targeted federal funds rates are not randomly distributed and they show signs of correlation. For example, among the 39 times of raising interest rate, there was one 17 consecutive intertest increase. Also, the minutes tend to emphasis on the unemployment of four major ethnicities when FOMC decided to raise or lower interest rates. On the other hand, there are 4102 variables involved in exploring the writing study of FOMC minutes. This means that the document-term matrix is a sparse matrix and high dimensionality requires a lot of computation time. Thus, adopted dimensionality reduction techniques: multiplication index, linear reduction and non-linear reduction methods. We found that the multiplication index has the best performance and, together with logistic regression, it has the highest accuracy in classifying the writing style of FOMC minutes in the cases of raising, lowering and holding interest rates. en_US dc.description.tableofcontents 第一章 緒論 1第一節 研究動機 1第一節 研究目的 1第二章 文獻探討 4第一節 聯邦準備系統與 FOMC 會議記錄 4第二節 文獻回顧 5第三節 資料介紹 9第三章 研究方法 10第一節 單一字詞、複合字、字詞 10第二節 資料預處理 11第三節 時間序列分析 15第四節 標準化相異詞出現率與景氣指標 16第五節 主題模型 17第六節 詞嵌入 21第七節 文本分類 22第四章 時間序列分析與探索式資料分析 25第一節 時間序列分析 25第二節 探索式資料分析 28第五章 主題模型與詞嵌入 31第一節 主題模型 31第二節 詞嵌入 33第六章 文本分類 36第七章 結論與討論 44第一節 結論 44第二節 討論 46參考文獻 47附錄一、名詞簡稱對照表 50附錄二、詞嵌入完整圖表 52 zh_TW dc.format.extent 11841682 bytes - dc.format.mimetype application/pdf - dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0107363015 en_US dc.subject (關鍵詞) 文字分析 zh_TW dc.subject (關鍵詞) 聯準會會議紀要 zh_TW dc.subject (關鍵詞) 寫作風格 zh_TW dc.subject (關鍵詞) 探索式資料分析 zh_TW dc.subject (關鍵詞) 維度縮減 zh_TW dc.subject (關鍵詞) Text mining en_US dc.subject (關鍵詞) FOMC minutes en_US dc.subject (關鍵詞) Writing style en_US dc.subject (關鍵詞) Exploratory data analysis en_US dc.subject (關鍵詞) Dimension reduction en_US dc.title (題名) 聯準會會議記要的文字分析 zh_TW dc.title (題名) Text Mining on FOMC Minutes en_US dc.type (資料類型) thesis en_US dc.relation.reference (參考文獻) 一、中文文獻柏南克（2013）。《柏南克的四堂課：聯準會與金融危機》。臺北：財信。孫亮、黃倩（2017）。《實用機器學習》。北京：人民電郵。黃于珊（2017）。「文字探勘在總體經濟上之應用—以美國聯準會會議紀錄為例」，政治大學金融學系碩士論文。二、英文文獻Abel, A. B., Bernanke, B., Croushore, D. (2013). Macroeconomics (8nd ed.). New Jersey, NJ: Pearson.Aggarwal, C. C. (2018). Machine Learning for Text. Cham, CH: Springer International Publishing. https://doi.org/10.1007/978-3-319-73531-3Bernanke, B. (2012). “The Federal Reserve and the Financial Crisis: The Aftermath of the Crisis, Lecture 4.” George Washington University School of Business.https://www.federalreserve.gov/mediacenter/files/chairman-bernanke-lecture4-20120329.pdfBlinder, A. S., Ehrmann, M., de Haan, J., Fratzscher, M., & Jansen, D.-J. (2008). “Central bank communication and monetary policy: A survey of theory and evidence,” Journal of Economic Literature, 46, 910–945. https://doi.org/10.1257/jel.46.4.910Board of Governors of the Federal Reserve System. (2021, January 14). “Federal Open Market Committee: Transcripts and other historical materials.” Board of Governors of the Federal Reserve System. https://www.federalreserve.gov/monetarypolicy/fomc_historical.htmBoukus, E., & Rosenberg, J. V. (2006). “The information content of FOMC minutes.” Federal Reserve Bank of New York. https://doi.org/10.2139/ssrn.922312Cannon, S. (2015). “Sentiment of the FOMC: Unscripted,” Economic Review [Federal Reserve Bank of Kansas City], Fall 2015, pp. 55.Chollet, F. (2018). Deep learning with Python. Shelter Island, NY: Manning Publications.Doh, T., Song, D., & Yang, S. K. (2020). “Deciphering Federal Reserve Communication via Text Analysis of Alternative FOMC Statements.” Federal Reserve Bank of Kansas City, Research Working Paper no. 20-14, October. https://doi.org/10.18651/RWP2020-14Ericsson, N. R. (2016). “Eliciting GDP forecasts from the FOMC’s minutes around the financial crisis,” International Journal of Forecasting, 32, 571–583. https://doi.org/10.1016/j.ijforecast.2015.09.007Ganegedara, T. (2018). Natural Language Processing with TensorFlow. Birmingham, UK: Packt Publishing.Hayoa, B., & Neuenkirch, M. (2013). “Do Federal Reserve Presidents Communicate with a Regional Bias?” Journal of Macroeconomics, 35(4), 62–72. https://doi.org/10.1016/j.jmacro.2012.10.002Huang, Y. L., & Kuan, C. M. (2021). “Economic Prediction with the FOMC Minutes: An Application of Text Mining,” International Review of Economics & Finance, 71, 751-761. https://doi.org/10.1016/j.iref.2020.09.020Hyndman, R. J., & Athanasopoulos, G. (2018). Forecasting: principles and practice (2nd ed.). Melbourne, AU: OTexts. https://otexts.com/fpp2/Joshi, P. (2016). Python Machine Learning Cookbook. Birmingham, UK: Packt Publishing.Jubinskia, D., & Tomljanovich, M. (2013). “Do FOMC Minutes Matter to Markets? An Intraday Analysis of FOMC Minutes Releases on Individual Equity Volatility and Returns,” Review of Financial Economics, 22(3), 86–97. https://doi.org/10.1016/j.rfe.2013.01.002Kliesen, K. L., Levine, B., & Waller, C. J. (2019). “Gauging Market Responses to Monetary Policy Communication,” Federal Reserve Bank of St. Louis Review, pp. 69-91.https://doi.org/10.20955/r.101.69-91Lucca, D. O., & Trebbi F. (2009). “Measuring Central Bank Communication: An Automated Approach with Application to FOMC Statements.” NBER Working Paper, No. 15367. https://doi.org/10.2139/ssrn.1470443Mikolov, T., Sutskever, I., Chen, K., Corrado, G. and Dean, J. (2013). “Distributed Representations of Words and Phrases and their Compositionality.” Proceedings of the 26th International Conference on Neural Information Processing Systems, NIPS’13, Curran Associates, Red Hook, NY, Vol. 2, pp. 3111-3119.Rosa, C. (2013). “The Financial Market Effect of FOMC Minutes,” FRBNY Economic Policy Review, 19(2), 67–81. https://ssrn.com/abstract=2378398Sarkar, D. (2019). Text Analytics with Python (2nd ed.). Bangalore, India: Apress.Shapiro, A.H., & Wilson, D.J. (2019). “Taking the Fed at its Word: A New Approach to Estimating Central Bank Objectives using Text Analysis.” Federal Reserve Bank of San Francisco Working Paper 2019-02. https://doi.org/10.24148/wp2019-02Stekler, H., & Symington, H. (2016). “Evaluating qualitative forecasts: The FOMC minutes, 2006–2010,” International Journal of Forecasting, 32, 559–570.https://doi.org/10.1016/j.ijforecast.2015.02.003VanderPlas, J. (2017). Python Data Science Handbook. California, CA: O’Reilly Media. zh_TW dc.identifier.doi (DOI) 10.6814/NCCU202101452 en_US
