미국 금리 스프레드를 이용한 한국 금리 스프레드 예측 모델에 관한 연구 : SVR-앙상블(RNN, LSTM, GRU) 모델 기반
A Study on the Korean Interest Rate Spread Prediction Model Using the US Interest Rate Spread : SVR-Ensemble (RNN, LSTM, GRU) Model based
2
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
Interest rate spreads indicate the conditions of the economy and serve as an indicator of the recession. The purpose of this study is to predict Korea's interest rate spreads using US data with long-term continuity. To this end, 27 US economic data were used, and the entire data was reduced to 5 dimensions through principal component analysis to build a dataset necessary for prediction. In the prediction model of this study, three RNN models (BasicRNN, LSTM, and GRU) predict the US interest rate spread and use the predicted results in the SVR ensemble model to predict the Korean interest rate spread. The SVR ensemble model predicted Korea's interest rate spread as RMSE 0.0658, which showed more accurate predictive power than the general ensemble model predicted as RMSE 0.0905, and showed excellent performance in terms of tendency to respond to fluctuations. In addition, improved prediction performance was confirmed through period division according to policy changes. This study presented a new way to predict interest rates and yielded better results. We predict that if you use refined data that represents the global economic situation through follow-up studies, you will be able to show higher interest rate predictions and predict economic conditions in Korea as well as other countries.
Abstract
Interest rate spreads indicate the conditions of the economy and serve as an indicator of the recession. The purpose of this study is to predict Korea's interest rate spreads using US data with long-term continuity. To this end, 27 US economic data were used, and the entire data was reduced to 5 dimensions through principal component analysis to build a dataset necessary for prediction. In the prediction model of this study, three RNN models (BasicRNN, LSTM, and GRU) predict the US interest rate spread and use the predicted results in the SVR ensemble model to predict the Korean interest rate spread. The SVR ensemble model predicted Korea's interest rate spread as RMSE 0.0658, which showed more accurate predictive power than the general ensemble model predicted as RMSE 0.0905, and showed excellent performance in terms of tendency to respond to fluctuations. In addition, improved prediction performance was confirmed through period division according to policy changes. This study presented a new way to predict interest rates and yielded better results. We predict that if you use refined data that represents the global economic situation through follow-up studies, you will be able to show higher interest rate predictions and predict economic conditions in Korea as well as other countries.
참고문헌 (22)
- Ahmad, N., "Factors influencing yield spreads of the malaysian bonds", Asian Academy of Management Journal, 14(2), pp.95~114 (2009)
- Althelaya, K.A., "Stock market forecast using multivariate analysis with bidirectional and stacked (LSTM, GRU)", 2018 21st Saudi Computer Society National Computer Conference (NCC), pp.18~7 (2018), IEEE
- Cheng, W., "Forecasting the 30-year U.S. treasury bond with a system of neural networks", NeuroVe $t Journal, 1(2) (1996)
- Cho, K., "Learning phrase representations using RNN encoder-decoder for statistical machine translation", arXiv preprint arXiv:1406.1078, ~ (2014)
- Dagum, E. B., "Modelling, forecasting and seasonally adjusting economic time series with the X-11 ARIMA method", Journal of the Royal Statistical Society. Series D(The Statistician), 27(3, pp.4) (1978), 203~216
- Estrella, A., "The term structure as a predictor of real economic activity", The Journal of Finance, 46(2), pp.555~576 (1991)
- Fah, C. F., "Factors correlated with treasury bond spreads in an emerging capital market", International Journal of Humanities and Social Science, 1(5), pp.154~164 (2008)
- Galbraith, J. W., "Testing for asymmetry in the link between the yield spread and output in the G-7countries", Journal of International Money and Finance, 19(5), pp.657~672 (2000)
- Harvey, C. R., "Term structure forecasts economic growth", Financial Analysts Journal, 49(3), pp.6~8 (1993)
- Hochreiter, S., "Long short-term memory", Neural Computation, 9(8), pp.735~1780 (1997)
- Ince, H., "Short term forecasting with support vector machines and application to stock price prediction", International Journal of General Systems, 37(6), pp.677~687 (2016)
- 지호준, "금리 스프레드의 경기예측력 평가", 재무관리연구, 19(2), pp.10~251 (2002), 한국재무관리학회
- 주일택, "양방향 LSTM 순환신경망 기반 주가예측모델", 한국정보전자통신기술학회 논문지, 11(2), pp.204~208 (2018), 한국정보전자통신기술학회
- 김홍지, "딥러닝 앙상블을 이용한 주가예측", 데이타베이스연구, 34(2), pp.111~120 (2018), 한국정보과학회
- 김준홍, "벡터자기회귀모형에 의한 금리스프레드의 예측", 한국데이터정보과학회지, 23(6), pp.1093~1102 (2012), 한국데이터정보과학회[DOI]
- 김진용, "신용스프레드의 경기예측력 분석", POSRI경영경제연구, 11(3), pp.36~63 (2011), 포스코경영연구소
- 이창용, "주성분 분석과 다중회귀모형을 사용한 자동차 건조 공정의 히트펌프 건조기 소모 전력 분석", 한국산업경영시스템학회지, 38(1), pp.143~151 (2015), 한국산업경영시스템학회
- Determinants of Emerging Market Bond Spread : Do Economic Fundamentals Matter?, "Min, H", The World Bank, ~ (1999)
- 박원주, "Macro-finance 모형을 이용한 국고채 수익률 추정 및 예측", 한국경제연구, 31(2), pp.187~210 (2013), 한국경제연구학회
- 신동하, "RNN과 LSTM을 이용한 주가 예측율 향상을 위한 딥러닝 모델", 한국정보기술학회논문지, 15(10), pp.9~16 (2017), 한국정보기술학회[DOI]
- Stock, J. H., "New indexes of coincident and leading economic indicators", NBER Macroeconomics Annual, 4, pp.351~394 (1989)
- Wang, J. H., "Stock market trend prediction using ARIMA-based neural networks", Proceedings of International Conference on Neural Networks (ICNN'96), 4, pp.2160~2165 (1996)