Fundamentals and machine learning in forecast of won-dollar exchange rate

다국어 초록 (Multilingual Abstract)

There are two issues in exchange rate forecast. One is the low explanatory power of economic fundamentals for high frequency exchange rate. The other is the usefulness of machine learning for exchange rate prediction. This paper tries to reconcile those issues by trying to use fundamentals to predict daily exchange rate with machine learning. To match monthly frequency fundamentals with daily exchange rate, linear interpolation is used to transform monthly data to daily. To reduce the noise, daily exchange rates are decomposed to trend and cyclical components using empirical model decomposition (EMD). Regression of trend part of exchange rate on fundamental variables show that the macroeconomic fundamentals have some explanatory power for daily exchange rate. For the forecast, long short-term memory (LSTM) of recurrent neural network (RNN) is applied to trend and cycle part separately. Based on the regression result, fundamental variables are used as input features of LSTM of trend component. Lagged variables are used for LSTM of cyclical part. Forecasts from the two LSTM models are added to get predictors of exchange rate. Results show that trend-cycle LSTM forecasts are better than the traditional random walk predictors.

참고문헌 (Reference)

• 1 김홍배 ; 류수열 ; 강상훈 ; 윤성민, "환율 변동 방향의 조건부확률 분석" 한국자료분석학회 12 (12): 3351-3362, 2010
• 2 최금화 ; 김순호, "인공신경망을 이용한 실적 공시 후 주가 예측" 한국자료분석학회 22 (22): 2667-2678, 2020
• 3 김영철 ; 이현준 ; 김지우 ; 안재준, "스왑포인트 결정요소를 이용한 머신러닝 기반의 원/달러 환율 예측 모형에 관한 연구: 다층퍼셉트론의 최적구조 탐색을 중심으로" 한국데이터정보과학회 29 (29): 203-216, 2018
• 4 노재확, "머신러닝을 이용한 우리나라 환율 예측 연구" 지식경영연구원 44 (44): 3-18, 2021
• 5 최승배 ; 강창완 ; 윤상후, "딥러닝을 이용한 공간예측" 한국자료분석학회 23 (23): 149-160, 2021
• 6 방원석 ; Reddy N. S. ; 신재익, "공유가치창출(CSV)이 사회적성과와 협력기업성과에 미치는 파급효과에 관한 연구- 인공신경망(ANN) 분석방법을 중심으로 -" 한국자료분석학회 23 (23): 1125-1141, 2021
• 7 Zhang, G. P., "Time series forecasting using a hybrid ARIMA and neural network model" 50 : 159-175, 2003
• 8 Huang, N. E., "The Empirical Mode Decomposition and the Hilbert Spectrum for Nonlinear andNonstationary Time Series Analysis" 454 : 903-995, 1998
• 9 Engel, C., "Taylor Rules and the Deutschmark-Dollar Real Exchange Rate" 38 (38): 1175-1194, 2006
• 10 Molodtsova, T., "Out-of-Sample Exchange Rate Predictability with Taylor Rule Fundamentals" 77 (77): 167-180, 2009
• 11 Qi, M., "Nonlinear prediction of exchange rates with monetary fundamentals" 10 : 623-640, 2003
• 12 Mark, N. C., "Nominal Exchange Rates and Monetary Fundamentals: Evidence from a Small Post-Bretton Woods Panel" 53 (53): 29-52, 2001
• 13 Jasic, T., "Neural network protocols and model performance" 55 : 747-753, 2003
• 14 Engel, C., "NBER Macroeconomics Annual 2007" 381-441, 2007
• 15 Hann, T. H., "Much ado about nothing? Exchange rates forecasting:neural networks vs. linear models using monthly and weekly data" 10 : 323-339, 1996
• 16 Engel, C., "Long Swings in the Dollar" 80 : 689-713, 1990
• 17 Gourinchas, P. O., "International Financial Adjustment" 115 (115): 665-703, 2007
• 18 Wang, Y. -C., "Fundamentals and Exchange Rate Prediction Revisited" 47 (47): 1651-1671, 2015
• 19 Zhang, B., "Foreign exchange rates forecasting with an EMD-LSTM neural networks model" 1053 (1053): 1-8, 2018
• 20 Yu, L., "Foreign Exchange Rate Forecasting with Artificial Neural Networks" Springer 2007
• 21 Kavtaradze, L., "Factor models and time-varying parameter framework for forecastingexchange rates and inflation: A survey" 32 (32): 302-334, 2018
• 22 Engel, C., "Factor model forecasts of Exchange Rates" 34 : 32-55, 2015
• 23 Meese, R. A., "Exchange Rates and International Economics" University of Chicago Press 1983
• 24 Meese, R. A., "Empirical Exchange Rate Models of the Seventies" 14 : 3-24, 1983
• 25 Diebold, F. X., "Comparing predictive accuracy" 13 : 253-263, 1995
• 26 Engel, C., "Can the Markov Switching Model Forecast Exchange Rates" 36 (36): 151-165, 1994
• 27 Walczak, S., "An Empirical Analysis of Data Requirements for Financial Forecasting with Neutral Networks" 17 (17): 203-322, 2001
• 28 Wu, Y., "Adaboost-Based Long Short-Term Memory Ensemble Learning Approach for Financial Time Series Forecasting" 115 (115): 159-165, 2018
• 29 곽내원 ; 임동훈, "AdaBoost-GRU 앙상블 모형을 이용한 금융 시계열 예측" 한국데이터정보과학회 32 (32): 267-281, 2021
• 30 Yao, J. T., "A case study on using neural networks to perform technical forecasting of forex" 34 : 79-98, 2000