텍스트 마이닝에 기반한 통화정책 기조가 한국 주식시장 및 부동산시장에 미치는 영향에 대한 분석
Effects of Monetary Policy Stance with Text Mining on Equity and Real Estate Markets - Evidence from Korea -
0
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
2008년 글로벌 금융위기 이후 장기간 지속된 저금리 기간 동안 주요국의 중앙은행은 주로 금리 이외의 타 정책수단인 비전통적 통화정책을 시행하였다. 다양한 통화정책수단이 시행되었음에도, 분석 수단의 한계로 인해 통화정책 효과의 분석은 대부분 기준금리 혹은 콜금리를 이용하여 이루어졌다. 본 연구에서는 Lee et al. (2019) 방법론에 기초하여 텍스트 마이닝을 통해 금융통화위원회 의사록에서 통화정책 기조를 추출한 뒤, 이러한 기조가 한국 주식시장 및 부동산시장에 미치는 영향을 분석하였다. 분석결과, 긴축적인 통화정책 기조에 반응하여 주가는 하락하고, 그 영향이 일정 기간 지속되는 것으로 나타났다. 부동산 매매 가격도 하락한 뒤, 약 10개월 간 영향이 지속되었으나, 주식시장에 비하면 상대적으로 적게 반응하는 것으로 나타났다. 나아가 기존의 금리를 이용할 경우 유의한 결과가 관찰되지 않던 부동산 매매시장의 반응을 분석할 수 있다는 점에서, 본 연구에서는 텍스트 마이닝을 이용하여 중앙은행의 커뮤니케이션을 직접 분석함으로써 추출해 낸 통화정책 기조가 정책효과를 수량화하여 측정하는 새로운 분석 수단으로 활용될 수 있다는 가능성을 제시한다.
Abstract
During the period of the zero lower bound (ZLB) on interest rates after the financial crisis of 2008, unconventional monetary policies were extensively implemented by central banks of major economies. However, previous studies that investigated the effectiveness of monetary policies have exceedingly relied on interest rates such as the base rate or call rate due to the lack of the analytical proxy. This study first constructs monetary policy stance (MPS) from the minutes of monetary policy meetings based on text mining following the methodology of Lee et al. (2019) and then investigates the effects of MPS on equity and real estates markets in Korea. The estimation results suggest that in response to a contractionary monetary policy shock, which is denoted as “hawkish”, equity prices fall and its impact persists over 4 months. In addition, real estate sales prices decline to a much lesser extent and its effect persists over 10 months. Finally, our findings suggest that MPS constructed through an analysis of the communication of the central bank based on text mining can be a new analytical measure in quantifying the effectivess of monetary policies, given that it is possible to analyze the response of the real estates market, which is not significant when interest rates are employed.
참고문헌 (24)
- 박준서, "글로벌 금융위기 전후의 통화정책과 거시경제변수 간의 구조적 관계 비교", 경제연구, 39(1), pp.229~253 (2021), 한국경제통상학회
- 박형달, "주식시장에 대한 통화정책의 파급효과분석", 산업경제연구, 26(4), pp.1587~1609 (2013), 한국산업경제학회
- 이영수, "통화정책과 주택시장: 부호제약을 이용한 베이지안 VAR 분석", 주택연구, 27(1), pp.113~136 (2019), 한국주택학회[DOI]
- 이용혁, "주택시장을 통한 통화정책 전달경로 분석 : SVAR 접근", 부동산·도시연구, 13(1), pp.25~45 (2020), 부동산도시연구원[DOI]
- 이태리, "통화정책의 주식시장 파급경로 연구", 주택연구, 23(3), pp.31~62 (2015)
- Baker, Scott R, "Measuring Economic Policy Uncertainty", Quarterly Journal of Economics, 131, pp.1593~1636 (2016)
- Bollen, Johan, "Twitter Mood Predicts the Stock Market", Journal of Computational Science, 2, pp.1~8 (2011)
- Cavallo, Alberto, "Online and Official Price Indexes: Measuring Argentina’s Inflation", Journal of Monetary Economics, 60, pp.152~165 (2013)
- Chague, Fernando, "Central Bank Communication Affects the Term-Structure of Interest Rates", Revista Brasileira de Economia, 69, pp.147~162 (2015)
- Cho, Dooyeon, "Macroeconomic Effects of Uncertainty Shocks: Evidence from Korea", Journal of Asian Economics, 84, pp.101571~ (2023)
- Choi, Hyunyoung, "Predicting the Present with Google Trends", Economic Record, 88, pp.2~9 (2012)
- Guzman Giselle, "Internet Search Behavior as an Economic Forecasting Tool: The Case of Inflation Expectations", Journal of Economic and Social Measurement, 36, pp.119~167 (2011)
- Hamilton, William L, "Inducing Domain-Specific Sentiment Lexicons from Unlabeled Corpora", Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp.595~605 (2016)
- Hansen, Stephen, "Shocking Language: Understanding the Macroeconomic Effects of Central Bank Communications", Journal of International Economics, 99, pp.s114~s133 (2016)
- Huang, Yu-Lieh, "Economic Prediction with the FOMC Minutes:An Application of Text Mining", International Review of Economics and Finance, 71, pp.751~761 (2021)
- Jakob, Niklas, "Beyond the Stars: Exploiting Free-Text User Reviews to Improve the Accuracy of Movie Recommendations", Proceedings of the 1st International CIKM Workshop on Topic-Sentiment Analysis for Mass Opinion, pp.57~64 (2009)
- 이영준, "Deciphering Monetary Policy Board Minutes with Text Mining: The Case of South Korea", The Korean Economic Review, 35(2), pp.471~511 (2019), 한국경제학회[DOI]
- Measuring Central Bank Communication: An Automated Approach with Application to FOMC Statements, "Lucca, David", NBER, ~, pp.NBER Working Papers, No. 15367 (2009)
- Picault, Matthieu, "Words Are Not All Created Equal: A New Measure of ECB Communication", Journal of International Money and Finance, 79, pp.136~156 (2017)
- Tang, Chuanyi, "Digging for Gold with a Simple Tool: Validating Text Mining in Studying Electronic Word-of-Mouth(eWOM) Communication", Marketing Letters, 26, pp.67~80 (2015)
- Thorsrud, Lief Anders, "Words are the New Numbers : A Newsy Coincident Index of the Business Cycle", Journal of Business and Economic Statistics, 38, pp.393~409 (2020)
- Turney, Peter D, "Thumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviews", Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp.417~424 (2002)
- Vosen, Simeon, "Forecasting Private Consumption: Survey-Based Indicators vs Google Trends", Journal of Forecasting, 30, pp.565~578 (2011)
- Wu, Jing Cynthia, "Measuring the Macroeconomic Impact of Monetary Policy at the Zero Lower Bound", Journal of Money, Credit and Banking, 48, pp.253~291 (2016)