텍스트 마이닝을 활용한 실질 국내총생산의 실시간 예측
Real-time Forecasting of Real GDP Using Text Mining
0
조회
0
다운로드
6
인용
0
참고문헌
키워드
초록
본 연구는 실질 GDP(RGDP: Real GDP)를 실시간으로 예측하는 모형을 개발하는 것을 목적으로 한다. 이를 위해 본 연구는 RGDP를 실시간으로 예측하는 것과 RGDP 예측의 설명변수로 선정된 심리 지표들을 실시간으로 예측하는 것으로 구분한다. 경제주체들의 심리지수들은 실물지표의 움직임을 잘 반영하기 때문에 RGDP 예측의 설명변수로 기업경기실사지수와 소비자동향지수를 활용한다. 또한 기업경기실사지수와 소비자동향조사를 예측하기 위해 온라인 뉴스의 비정형 텍스트 데이터를 활용한다. 본 연구는 기업경기실사지수와 소비자동향지수를 바탕으로 RGDP를 실시간으로 예측하기 위해 다음과 같은 2단계 절차를 수행한다. 1단계에서는 기업경기실사지수와 소비자동향지수에 영향을 미치는 요인을 빠르게 반영하기 위해 온라인 뉴스의 비정형 데이터로부터 정보를 수집하는 텍스트 마이닝 기법을 활용한다. 이렇게 텍스트 마이닝을 통해 비정형 데이터를 정량화한 후, 이를 바탕으로 딥러닝 기법을 활용하여 기업경기실사지수와 소비자동향지수를 추정한다. 2단계에서는 선행연구에서 활용된 RGDP 예측 방법인 시차회귀모형(LR: Lagged Regression), 자기회귀 동적요소모형(AR-DFM: Autoregressive Dynamic factor model), 혼합자료샘플링(MIDAS: Mixed-Data Sampling) 모형을 활용한다. 이 중에서 RGDP 예측의 최종 모형을 선정하기 위해 각 모형에 대한 추정 오차의 RMSE(Root Mean Squared Error)를 산출한다. 분석 결과, 시차회귀모형이 실시간 예측에 가장 적합한 것으로 나타났다.
Abstract
This study is trying to develop a model that predicts real GDP (RGDP) in real time. To this end, this study is divided into the real-time prediction of RGDP and the real-time prediction of ESI(Economic Sentiment indicator) selected as explanatory variables for RGDP prediction. Since the sentiment indices of economic agents reflect the movement of real economy well, they use BSI(Business Survey Index) and CSI(Consumer Survey Index) as explanatory variables for RGDP prediction. In addition, unstructured data from online news are used to predict BSI and CSI. This study performs the following two-step procedure to predict RGDP in real time based on the BSI and the CSI. In the first stage, text mining techniques are used to collect information from unstructured data in online news to analyze the factors affecting them. After quantifying unstructured data through text mining in this way, a deep learning technique is utilized to estimate the BSI and the CSI. In the second stage, the lagged regression(LR) model, the autoregressive dynamic factor model (AR-DFM) model, and the mixed-data sampling (MIDAS) model, which are methods of predicting RGDP used in previous studies, are used. Among them, Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Relative Mean Absolute Error (RMAE) of estimation errors for each model are calculated to select the final model of RGDP prediction. The analysis results show that the LR model is most suitable for the real-time prediction of RGDP.
참고문헌 (33)
- 김치호, "GDP 성장률의 Nowcasting에 관한 연구", 국민계정리뷰, 2, pp.1~22 (2016), 한국은행
- 이동수, "전산업생산지수를 이용한 분기 성장률 예측", 통계연구, 18(2), pp.66~88 (2013), 통계청
- 이승윤, "기계학습과 혼합주기 모형을 활용한 단기전망시스템", 조사통계월보, 5, pp.16~41 (2017)
- 최광신, "K-SuperCast: 빅데이터를 이용한 GDP 성장률 적시예측 시스템", 한국데이터정보과학회지, 30(4), pp.723~743 (2019), 한국데이터정보과학회
- 최병진, "월별자료를 이용한 예측조합에 의한 GDP 전망", 조사통계월보, 10, pp.16~48 (2014), 한국은행
- 형남원, "혼합자료 샘플링 모형을 통한 GDP 예측", 국제경제연구, 22(2), pp.83~117 (2016), 한국국제경제학회[DOI]
- 황종률, "월간경제지표를 이용한 실질GDP성장률 예측", 예산정책연구, 1(2), pp.103~133 (2012), 국회예산정책처[DOI]
- Nowcasting New Zealand GDP using machine learning algorithms, "Adam Richardson", CAMA, ~, pp.CAMA Working Papers 2018-47 (2018)
- Camacho, Maximo, "Short-term Forecasting for Empirical Economists: A Survey of the Recently Proposed Algorithms", oundations and Trends(R) in Econometrics, 6(2), pp.101~161 (2013)
- Machine learning at central banks, "Chakraborty, Chiranjit", Bank of England, ~, pp.Bank of England working papers, 674 (2017)
- The use of statistical forecasting models at the Reserve Bank of New Zealand, "Chris Bloor", Reserve Bank of New Zealand, 21~26, pp.Reserve Bank of New Zealand Bulletin 72 (2009)
- Big data econometrics: Nowcasting and early estimates, "D. Buono", Universita Bocconi, ~, pp.Technical Report, 82 (2018)
- Diron, M., "Short-term forecasts of Euro area real GDP growth : An assessment of real-time performance based on vintage data", Journal of Forecasting, 27, pp.371~390 (2008)
- Eickmeier, Sandra, "Forecasting national activity using lots of international predictors: An application to New Zealand", International Journal of Forecasting, 27(2), pp.496~511 (2011), Elsevier
- Elena Andreou, "Should Macroeconomic Forecasters Use Daily Financial Data and How?", Journal of Business & Economic Statistics, 31(2), pp.240~251 (2013)
- Frank Schorfheide, "Real-Time Forecasting With a Mixed-Frequency VAR", Journal of Business & Economic Statistics, 33(3), pp.366~380 (2015)
- Foroni C, "A comparison of mixed frequency approaches for nowcasting Euro area macroeconomic aggregates", International Journal of Forecasting, 30, pp.554~568 (2014)
- Jansen, W. Jos, "Forecasting and nowcasting real GDP: Comparing statistical models and subjective forecasts", International Journal of Forecasting, 32(2), pp.411~436 (2016)
- GDPNow: A model for GDP nowcasting, "Higgins P.", Federal Reserve Bank of Atlanta, ~, pp.Federal Reserve Bank of Atlanta Working Paper, 2014-7 (2014)
- Keynes, J. M., "The General Theory of Employment, Interest, and Money" (1936), Harcourt, Brace and Co
- Koop, Gary, "Bayesian Multivariate Time Series Methods for Empirical Macroeconomics", Foundations and Trends(R) in Econometrics, 3(4), pp.267~358 (2010)
- When are Google data useful to nowcast GDP? An approach via pre-selection and shrinkage, "Laurent Ferra", Center for Research in Economics and Statistics, ~, pp.Working Papers 2019-04 (2019)
- Mirjana Pejić Bach, "Text Mining for Big Data Analysis in Financial Sector : A Literature Review", Sustainability, 11(5), pp.1~27 (2019)
- Giannone, D., "A new coincident index of business cycles based on monthly and quarterly series", Journal of Applied Econometrics, 18, pp.427~443 (2017)
- Paolo Fornaro, "Nowcasting Finnish Real Economic Activity: a Machine Learning Approach", Empirical Economics, 58(1), pp.55~71 (2020)
- R. Golinelli, "Tracking world trade and GDP in real time", International Journal of Forecasting, 30(4), pp.847~862 (2014)
- S. Scott, "Economic Analysis of the Digital Economy", pp.119~135 (2015)
- Vishwanath Bijalwan, "A Machine Learning Approach for Text and Document Mining", International Journal of Computer Science Engineering, 6(5), pp.115~123 (2017)
- Stock, R. S., "Dynamic factor models, Oxford handbook on economic forecasting" (2011), Oxford University Press
- Tianqi Chen, "XGBoost: A Scalable Tree Boosting System", 22nd SIGKDD Conference on Knowledge Discovery and Data Mining (2016)
- Tomas Mikolov, "Efficient estimation of word representations in vector space", arXiv:1301.3781v3, ~ (2013)
- Nowcasting Canadian Economic Activity in an Uncertain Environment, "Tony Chernis", Bank of Canada, ~, pp.Discussion Papers 18-9 (2018)
- Troy D. Matheson, "Factor Model Forecasts for New Zealand", International Journal of Central Banking, 2(2), pp.169~237 (2006)