딥러닝을 이용한 이변량 장기종속시계열 예측 = Bivariate long range dependent time series forecasting using deep learning

다국어 초록 (Multilingual Abstract)

We consider bivariate long range dependent (LRD) time series forecasting using a deep learning method. A long short-term memory (LSTM) network well-suited to time series data is applied to forecast bivariate time series; in addition, we compare the forecasting performance with bivariate fractional autoregressive integrated moving average (FARIMA) models. Out-of-sample forecasting errors are compared with various performance measures for functional MRI (fMRI) data and daily realized volatility data. The results show a subtle difference in the predicted values of the FIVARMA model and VARFIMA model. LSTM is computationally demanding due to hyper-parameter selection, but is more stable and the forecasting performance is competitively good to that of parametric long range dependent time series models.

국문 초록 (Abstract)

본 논문에서는 딥러닝을 이용한 이변량 장기종속시계열(long-range dependent time series) 예측을 고려하였다. 시계열 데이터 예측에 적합한 LSTM(long short-term memory) 네트워크를 이용하여 이변량 장기종속시계열을 예측하고 이를 이변량 FARIMA(fractional ARIMA) 모형인 FIVARMA 모형과 VARFIMA 모형과의 예측 성능을 실증 자료 분석을 통해 비교하였다. 실증 자료로는 기능적 자기공명 영상(fMRI) 및 일일 실현 변동성(daily realized volatility) 자료를 이용하였으며 표본외 예측(out-of sample forecasting) 오차 비교를 통해 예측 성능을 측정하였다. 그 결과, FIVARMA 모형과 VARFIMA 모형의 예측값에는 미묘한 차이가 존재하며, LSTM 네트워크의 경우 초매개변수 선택으로 복잡해 보이지만 계산적으로 더 안정되면서 예측 성능도 모수적 장기종속시계열과 뒤지지 않은 좋은 예측 성능을 보였다.

참고문헌 (Reference)

1 Termenon, N., "Reliability of graph analysis of resting state fMRI using test-retest dataset from the Human Connectome Project" 142 : 172-187, 2016

2 Smith, E. M., "Predicting the occurrence of world news events using recurrent neural networks and auto-regressive moving average models" 191-202, 2017

3 Whittle, P., "On the fitting of multivariate autoregressions, and the approximate canonical factorization of a spectral density matrix" 50 : 129-134, 1963

4 Hochreiter, S., "Long short-term memory" 9 : 1735-1780, 1997

5 Gers, F. A., "Learning to forget : continual prediction with LSTM" 12 : 2451-2471, 2000

6 Hinton, G. E., "Improving neural networks by preventing co-adaptation of feature detectors"

7 Hosking, J. R. M., "Fractional differencing" 68 : 165-176, 1981

8 Aladag, C. H., "Forecasting nonlinear time series with a hybrid methodology" 22 : 1467-1470, 2009

9 Kechagias, S., "Definitions and representations of multivariate long?range dependent time series" 36 : 1-25, 2015

10 Lobato, I. N., "Consistency of the averaged cross-periodogram in long memory series" 18 : 137-155, 1997

11 Sela, R. J., "Computationally efficient methods for two multivariate fractionally integrated models" 30 : 631-651, 2008

12 Baek, C., "Asymptotics of bivariate local Whittle estimators with applications to fractal connectivity"

13 Hyndman, R. J., "Another look at forecast-accuracy metrics for intermittent demand" 4 : 43-46, 2006

14 Granger, C. W. J., "An introduction to long?memory time series models and fractional differencing" 1 : 15-39, 1980

15 Kingma, D., "Adam : A method for stochastic optimization"

16 Kohzadi, N., "A comparison of artificial neural network and time series models for forecasting commodity prices" 10 : 169-181, 1996

17 Ho, S. L., "A comparative study of neural network and Box-Jenkins ARIMA modeling in time series prediction" 42 : 371-375, 2002