Impact of Structural Break Location on Forecasting Accuracy: Traditional Methods Versus Artificial Neural Network

Year 2022, Volume: 06 Issue: 2, 83 - 96, 31.12.2022

Daud Ali Aser Esin Firuzan

https://doi.org/10.34110/forecasting.1162548

Abstract

Since forecasting future values is fundamental for researchers, investors, practitioners, etc., obtaining accurate predictions is critical in time series analysis. The accuracy is reliant on good modelling and good-quality data. The latter is affected by unusual observations, changes over time, missing data, and structural breaks among others. Economic crises are the major cause of data instability and therefore, this paper focuses on how structural breaks in conditional heteroscedastic financial and macroeconomic data affect forecasting accuracy on short and long-term horizons. More specifically, we are interested in the impact of the location of the structural break and break size on the predictive performance of two linear (ARIMA and Exponential Smoothing) forecasting models and two nonlinear (ARIMA – ARCH and Artificial Neural Network) models. We conducted Monte Carlo simulations and showed that the forecasting accuracy decreases as the structural break location approaches the end of the sample. In addition, break size and length of the horizon show the same impact on the forecasting accuracy as the forecasting error increases with the increase of break magnitude and length of the horizon. We also showed that ARIMA – ARCH model is the best performing in the absence of a structural break while the artificial neural network model outperforms all the competing models in the presence of structural break, especially in large break sizes and long horizons. Last, we applied the above techniques to forecasting daily close prices of brent oil and Turkish Lira – USD exchange rates out–of–sample, and similar results were found.

Keywords

Structural break, break location, conditional heteroscedasticity, artificial neural network, forecasting accuracy, break size.

References

• [1] J.H. Stock, M.W. Watson, Evidence on Structural Instability in Macroeconomic Time Series Relations, Journal of Business & Economic Statistics, 14 (1996), 11–30.
• [2] D. Pettenuzzo, A.Timmermann, Predictability of Stock Returns and Asset Allocation under Structural Breaks ∗, Journal of Econometrics, (2010). pp. 60–78. doi: 10.1016/j.jeconom.2011.02.019.
• [3] G. Koop, S. Potter, Are Apparent Findings of Nonlinearity Due to Structural Instability in Economic Time Series?, SSRN Electron. J. 4 (2005) 37–55. doi:10.2139/ssrn.163151.
• [4] B. Siliverstovs, D. van Dijk, Forecasting Industrial Production with Linear, Nonlinear, and Structural Change Models, Econom. Inst. Rep. EI 2003-16. (2002).
• [5] M.P. Clements, and D.F. Hendry, Forecasting Economic Time Series, Cambridge University Press (1998).
• [6] B.E. Hansen, The New Econometrics of Structural Change, J. Econ. Perspect. 15 (2001) 117–128.
• [7] A. Yin, Out-of-Sample Forecast Model Averaging with Parameter Instability, (2014) 1–40.
• [8] J. Nyblom, Testing for the Constancy of Parameters Over Time, 84 (1989) 223–230.
• [9] B.Y.J. Bai, P. Perron, Estimating and Testing Linear Models with Multiple Structural Changes Author ( s ): Jushan Bai and Pierre Perron Published by : The Econometric Society Stable URL : https://www.jstor.org/stable/2998540, 66 (1998) 47–78.
• [10] P.R. Winters, Forecasting Sales by Exponentially Weighted Moving Averages INFORMS Stable URL : https://www.jstor.org/stable/2627346, 6 (1960) 324–342.
• [11] C.C. Holt, Forecasting seasonals and trends by exponentially weighted moving averages, 20 (2004) 5–10. doi:10.1016/j.ijforecast.2003.09.015.
• [12] R.J. Hyndman, G. Athanasopoulos, Forecasting : Principles and Practice, OTexts, Melbourne, (2018).
• [13] R.J. Hyndman, A.B. Koehler, J.K. Ord, R.D. Snyder, Forecasting with Exponential Smoothing: the state space approach, Springer-Verlag, Berlin, (2008).
• [14] G. Box, G. Jenkins, Time series analysis: forecasting and control. Holden-Day (1970).
• [15] R.J. Hyndman, Automatic Time Series Forecasting : the forecast Package for R, 27 (2008). doi:10.18637/jss.v000.i00.
• [16] R.F. Engle, Autoregressive Conditional Heteroscedasticity with Estimates of the Variance of United Kingdom Inflation. The Econometric Society, 50 (1982) 987–1007.
• [17] T. Bollerslev, Generalized Autoregressive Conditional Heteroskedasticity, Journal of Econometrics , 31 (1986) 307–327.