DOI QR코드

DOI QR Code

Comparison Studies of Hybrid and Non-hybrid Forecasting Models for Seasonal and Trend Time Series Data

트렌드와 계절성을 가진 시계열에 대한 순수 모형과 하이브리드 모형의 비교 연구

  • 정철우 (한국국방연구원 국방운영연구센터) ;
  • 김명석 (서강대학교 경영전문대학원 글로벌 서비스 경영학과)
  • Received : 2013.01.29
  • Accepted : 2013.03.13
  • Published : 2013.03.31

Abstract

In this article, several types of hybrid forecasting models are suggested. In particular, hybrid models using the generalized additive model (GAM) are newly suggested as an alternative to those using neural networks (NN). The prediction performances of various hybrid and non-hybrid models are evaluated using simulated time series data. Five different types of seasonal time series data related to an additive or multiplicative trend are generated over different levels of noise, and applied to the forecasting evaluation. For the simulated data with only seasonality, the autoregressive (AR) model and the hybrid AR-AR model performed equivalently very well. On the other hand, if the time series data employed a trend, the SARIMA model and some hybrid SARIMA models equivalently outperformed the others. In the comparison of GAMs and NNs, regarding the seasonal additive trend data, the SARIMA-GAM evenly performed well across the full range of noise variation, whereas the SARIMA-NN showed good performance only when the noise level was trivial.

본 연구에서는 시계열 예측을 위해 선형 모형과 비선형 모형의 하이브리드 모형 및 순수 모형의 성과를 비교 평가하였다. 이를 위해 5가지 서로 다른 패턴을 가지는 데이터를 생성하여 시뮬레이션을 진행하였다. 본 연구에서 고려한 선형 모형은 AR(autoregressive model)과 SARIMA(seasonal autoregressive integrated moving average model)이고 비선형 모형은 인공신경망(artificial neural networks model)과 GAM(generalized additive model)이다. 특히, GAM은 여러 장점에도 불구하고 시계열 예측을 위한 비선형 모형으로 기존 연구들에서는 거의 쓰이지 않았던 모형이다. 시뮬레이션 결과, seasonality를 가지는 시계열에 대해서는 AR 및 AR-AR 모형이, trend를 가지는 시계열에 대해서는 SARIMA 및 SARIMA와 다른 모형의 하이브리드 모형이 다른 모형에 비해 높은 성과를 보였다. 한편, 인공신경망과 GAM을 비교하면, 트렌드와 계절성이 더해진 시계열에 대해 SARIMA와 GAM의 하이브리드 모형이 거의 모든 노이즈(noise) 수준에 대해 높은 성과를 보인 반면, 노이즈 수준이 미미한 경우에 한해 SARIMA와 인공신경망의 하이브리드 모형이 높은 성과를 보였다.

Keywords

References

  1. Adya, M. and F. Collopy, "How effective are neural networks at forecasting and prediction? A review and evaluation", Journal of Forecasting, Vol.17(1998), 481-495. https://doi.org/10.1002/(SICI)1099-131X(1998090)17:5/6<481::AID-FOR709>3.0.CO;2-Q
  2. Barbounis, T. G. and J. B. Teocharis, "Locally recurrent neural networks for wind speed prediction using spatial correlation", Information Science, Vol.177(2007), 5775-5797. https://doi.org/10.1016/j.ins.2007.05.024
  3. Berg, D., "Bankruptcy prediction by generalized additive models", Applied Stochastic Models in Business and Industry, Vol.23(2007), 129-143.
  4. Bodyanskiy, Y. and S. Popov, "Neural network approach to forecasting of quasiperiodic financial time series", European Journal of Operational Research, Vol.175(2006), 1357-1366. https://doi.org/10.1016/j.ejor.2005.02.012
  5. Box, G. E. P. and G. M. Jenkins, Time Series Analysis : Forecasting and Control, San Francisco, CA : Holden-Day, 1976.
  6. Celik, A. E. and Y. Karatepe, "Evaluating and forecasting banking crises through neural network models : an application for Turkish banking sector", Expert Systems with Applications, Vol.33(2007), 809-815. https://doi.org/10.1016/j.eswa.2006.07.005
  7. Di Narzo, A. F., J. L. Aznarte, and M. Stigler, Nonlinear time series models with regime switching, R package version (http://cran.us.rproject. org/web/packages/tsDyn/), 2012.
  8. Dominici, F., A. McDermott, S. L. Zeger, and J. M. Samet, "On the use of generalized additive models in time-series studies of air pollution and health", American Journal of Epidemiology, Vol.156(2002), 193-203. https://doi.org/10.1093/aje/kwf062
  9. Freitas, P. S. A. and A. J. L. Rodrigues, "Model combination in neural-based forecasting", European Journal of Operational Research, Vol. 173(2006), 801-814. https://doi.org/10.1016/j.ejor.2005.06.057
  10. Hansen, J. V., J. B. McDonald, and R. D. Nelson, "Time series prediction with genetic-algorithm designed neural networks : an empirical comparison with modern statistical models", Computational Intelligence, Vol.15(1999), 171-184. https://doi.org/10.1111/0824-7935.00090
  11. Hastie, T. and Tibshirani, R., "Generalized additive models", Statistical Science, Vol.1(1986), 297-310. https://doi.org/10.1214/ss/1177013604
  12. Hyndman, R. J., Forecasting functions for time series and linear models, R package version (http://cran.r-project.org/web/packages/forec ast/), (2012).
  13. Ittig, P. T., "A seasonal index for business", Decision Sciences, Vol.28(1997), 335-355. https://doi.org/10.1111/j.1540-5915.1997.tb01314.x
  14. Montgomery, D. C., L. A. Johnson, and J. S. Gardiner, Time Series Analysis. McGraw- Hill, New York, 1990.
  15. Nelson, C. R. and C. I. Plosser, "Trends and random walks in macroeconomic time series: Some evidence and implications", Journal of Monetary Economics, Vol.10(1982), 139-162. https://doi.org/10.1016/0304-3932(82)90012-5
  16. Nelson, M., T. Hill, W. Renus, and M. O'Connor, "Time series forecasting using neural networks : should the data be deseasonalized first?", Journal of Forecasting, Vol.18(1999), 359-367. https://doi.org/10.1002/(SICI)1099-131X(199909)18:5<359::AID-FOR746>3.0.CO;2-P
  17. Prada-Sanchez, J. M. and M. Febrero-Bande, "Parametric, non-parametric and mixed approaches to prediction of sparsely distributed pollution incidents : a case study", Journal of Chemometrics, Vol.11(1997), 13-32. https://doi.org/10.1002/(SICI)1099-128X(199701)11:1<13::AID-CEM430>3.0.CO;2-K
  18. Tseng, F. M., H. C. Yu, and G. H. Tzeng, "Combining neural network model with seasonal time series ARIMA model", Technological Forecasting and Social Change, Vol.69(2002), 71-87. https://doi.org/10.1016/S0040-1625(00)00113-X
  19. Wood, S. N., Generalized additive models : An introduction with R. Florida : Chapman and Hall/CRC, 2006.
  20. Zhang, G. P., "Time series forecasting using a hybrid ARIMA and neural network model", Neurocomputing, Vol.50(2003), 159-175. https://doi.org/10.1016/S0925-2312(01)00702-0