Error modeling approach to improve time series forecasters

Abstract In time series forecasting exercises it has been usual to suppose that the error series generated by the forecasters have a white noise behavior. However, it is possible that such supposition is violated in practice due to model misspecification or disturbances of the phenomenon not captured by the predictive models. It may lead to statistically biased and/or inefficient predictors. The present paper introduces an approach to correct predetermined forecasters by recursively modeling their remaining residuals. Two formalisms are used to illustrate the recursive approach: the well-known (linear) autoregressive integrated moving average (ARIMA) and the (non-linear) Artificial Neural Network (ANN). These models are recursively adjusted to the remaining residuals of a given forecaster until a white noise behavior is achieved. Applications involving ARIMA and ANN forecasters for Dow Jones Industrial Average Index, S&P500 Index, Google Stock Value, Nasdaq Index, Wolf׳s Sunspot, and Canadian Lynx data series indicate the usefulness of the proposed framework.

[1]  Gwilym M. Jenkins,et al.  Time series analysis, forecasting and control , 1972 .

[2]  George D. C. Cavalcanti,et al.  An intelligent perturbative approach for the time series forecasting problem , 2010, The 2010 International Joint Conference on Neural Networks (IJCNN).

[3]  B. LeBaron,et al.  A test for independence based on the correlation dimension , 1996 .

[4]  Paulo S. G. de Mattos Neto,et al.  Correcting and combining time series forecasters , 2014, Neural Networks.

[5]  R. Engle.  Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflation , 1982 .

[6]  Marco Dorigo,et al.  Ant system: optimization by a colony of cooperating agents , 1996, IEEE Trans. Syst. Man Cybern. Part B.

[7]  Tiago Alessandro Espínola Ferreira,et al.  A New Intelligent System Methodology for Time Series Forecasting with Artificial Neural Networks , 2008, Neural Processing Letters.

[8]  Michael Y. Hu,et al.  A simulation study of artificial neural networks for nonlinear time-series forecasting , 2001, Comput. Oper. Res..

[9]  Hans-Paul Schwefel,et al.  Evolution strategies – A comprehensive introduction , 2002, Natural Computing.

[10]  Kung-Sik Chan,et al.  Time Series Analysis: With Applications in R , 2010 .

[11]  Paulo Cortez,et al.  Global and decomposition evolutionary support vector machine approaches for time series forecasting , 2014, Neural Computing and Applications.

[12]  Paulo S. G. de Mattos Neto,et al.  Combining Artificial Neural Network and Particle Swarm System for time series forecasting , 2009, 2009 International Joint Conference on Neural Networks.

[13]  Víctor Leiva,et al.  An R Package for a General Class of Inverse Gaussian Distributions , 2008 .

[14]  Araceli Sanchis,et al.  Time series forecasting using a weighted cross-validation evolutionary artificial neural network ensemble , 2013, Neurocomputing.

[15]  David Hsieh.  Testing for Nonlinear Dependence in Daily Foreign Exchange Rates , 1989 .

[16]  Kunikazu Kobayashi,et al.  Time series forecasting using a deep belief network with restricted Boltzmann machines , 2014, Neurocomputing.

[17]  Farshid Keynia,et al.  Application of a new hybrid neuro-evolutionary system for day-ahead price forecasting of electricity markets , 2010, Appl. Soft Comput..

[18]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[19]  R. Clemen.  Combining forecasts: A review and annotated bibliography , 1989 .

[20]  T. Bollerslev,et al.  Generalized autoregressive conditional heteroskedasticity , 1986 .

[21]  Young-Oh Kim,et al.  Combining single-value streamflow forecasts - a review and guidelines for selecting techniques. , 2009 .

[22]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[23]  C. H. Shirazi A. Mosleh.  Data-informed calibration of experts in Bayesian framework , 2009 .

[24]  Mu-Chen Chen,et al.  A data mining based approach for travel time prediction in freeway with non-recurrent congestion , 2014, Neurocomputing.

[25]  Kenneth F. Wallis,et al.  Combining forecasts – forty years later , 2011 .

[26]  Xin Yao,et al.  Fast Evolution Strategies , 1997, Evolutionary Programming.

[27]  Tiago Alessandro Espínola Ferreira,et al.  An experimental study of fitness function and time series forecasting using artificial neural networks , 2010, GECCO '10.

[28]  Michael Y. Hu,et al.  Forecasting with artificial neural networks: The state of the art , 1997 .

[29]  Zbigniew Michalewicz,et al.  Genetic Algorithms + Data Structures = Evolution Programs , 1996, Springer Berlin Heidelberg.

[30]  Gwilym M. Jenkins,et al.  Time series analysis, forecasting and control , 1971 .

[31]  George D. C. Cavalcanti,et al.  Hybrid intelligent system for air quality forecasting using phase adjustment , 2014, Eng. Appl. Artif. Intell..

[32]  Ali Mosleh,et al.  The Assessment of Probability Distributions from Expert Opinions with an Application to Seismic Fragility Curves , 1986 .

[33]  Guoqiang Peter Zhang,et al.  Time series forecasting using a hybrid ARIMA and neural network model , 2003, Neurocomputing.

[34]  Enrique López Droguett,et al.  Bayesian Methodology for Model Uncertainty Using Model Performance Data , 2008, Risk analysis : an official publication of the Society for Risk Analysis.

[35]  Rob J Hyndman,et al.  Automatic Time Series Forecasting: The forecast Package for R , 2008 .