An intelligent hybridization of ARIMA with machine learning models for time series forecasting

Abstract The development of accurate forecasting systems can be challenging in real-world applications. The modeling of real-world time series is a particularly difficult task because they are generally composed of linear and nonlinear patterns that are combined in some form. Several hybrid systems that combine linear and nonlinear techniques have obtained relevant results in terms of accuracy in comparison with single models. However, the best combination function of the forecasting of the linear and nonlinear patterns is unknown, which makes this modeling an open question. This work proposes a hybrid system that searches for a suitable function to combine the forecasts of linear and nonlinear models. Thus, the proposed system performs: (i) linear modeling of the time series; (ii) nonlinear modeling of the error series; and (iii) a data-driven combination that searches for: (iii.a) the most suitable function, between linear and nonlinear formalisms, and (iii.b) the number of forecasts of models (i) and (ii) that maximizes the performance of the combination. Two versions of the hybrid system are evaluated. In both versions, the ARIMA model is used in step (i) and two nonlinear intelligent models – Multi-Layer Perceptron (MLP) and Support Vector Regression (SVR) – are used in steps (ii) and (iii), alternately. Experimental simulations with six real-world complex time series that are well-known in the literature are evaluated using a set of popular performance metrics. Our results show that the proposed hybrid system attains superior performance when compared with single and hybrid models in the literature.

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

[2]  Rati Wongsathan,et al.  A Hybrid ARIMA and Neural Networks Model for PM-10 Pollution Estimation: The Case of Chiang Mai City Moat Area , 2016 .

[3]  Ying Wang,et al.  A Hybrid Model for Predicting the Prevalence of Schistosomiasis in Humans of Qianjiang City, China , 2014, PloS one.

[4]  Teresa Bernarda Ludermir,et al.  A hybrid evolutionary decomposition system for time series forecasting , 2016, Neurocomputing.

[5]  Nikolaos Kourentzes,et al.  Neural network ensemble operators for time series forecasting , 2014, Expert Syst. Appl..

[6]  Rohitash Chandra,et al.  Evaluation of co-evolutionary neural network architectures for time series prediction with mobile application in finance , 2016, Appl. Soft Comput..

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

[8]  Mehdi Khashei,et al.  An artificial neural network (p, d, q) model for timeseries forecasting , 2010, Expert Syst. Appl..

[9]  F. Takens.  Detecting strange attractors in turbulence , 1981 .

[10]  Ping-Feng Pai,et al.  A hybrid ARIMA and support vector machines model in stock price forecasting , 2005 .

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

[12]  Tugba Taskaya-Temizel,et al.  2005 Special Issue: A comparative study of autoregressive neural network hybrids , 2005 .

[13]  Yong Yu,et al.  A hybrid SARIMA wavelet transform method for sales forecasting , 2011, Decis. Support Syst..

[14]  David Horn,et al.  Combined Neural Networks for Time Series Analysis , 1993, NIPS.

[15]  George D. C. Cavalcanti,et al.  A perturbative approach for enhancing the performance of time series forecasting , 2017, Neural Networks.

[16]  George D. C. Cavalcanti,et al.  Nonlinear combination method of forecasters applied to PM time series , 2017, Pattern Recognit. Lett..

[17]  Ignacio J. Turias,et al.  Hybrid approaches based on SARIMA and artificial neural networks for inspection time series forecasting , 2014 .

[18]  Himansu Sekhar Behera,et al.  A hybrid ETS-ANN model for time series forecasting , 2017, Eng. Appl. Artif. Intell..

[19]  Mehdi Khashei,et al.  A novel hybridization of artificial neural networks and ARIMA models for time series forecasting , 2011, Appl. Soft Comput..

[20]  Konstantinos Ioannou,et al.  Predicting fuelwood prices in Greece with the use of ARIMA models, artificial neural networks and a hybrid ARIMA–ANN model , 2009 .

[21]  D. Steinberg.  CART: Classification and Regression Trees , 2009 .

[22]  Durdu Ömer Faruk.  A hybrid neural network and ARIMA model for water quality time series prediction , 2010, Eng. Appl. Artif. Intell..

[23]  Ying Wang,et al.  Application of a New Hybrid Model with Seasonal Auto-Regressive Integrated Moving Average (ARIMA) and Nonlinear Auto-Regressive Neural Network (NARNN) in Forecasting Incidence Cases of HFMD in Shenzhen, China , 2014, PloS one.

[24]  J. M. Bates,et al.  The Combination of Forecasts , 1969 .

[25]  Paulo S. G. de Mattos Neto,et al.  Error modeling approach to improve time series forecasters , 2015, Neurocomputing.

[26]  Zhenhong Du,et al.  Red tide time series forecasting by combining ARIMA and deep belief network , 2017, Knowl. Based Syst..

[27]  Teresa Bernarda Ludermir,et al.  A Hybrid Evolutionary System for Parameter Optimization and Lag Selection in Time Series Forecasting , 2014, 2014 Brazilian Conference on Intelligent Systems.

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

[29]  Kuan-Yu Chen,et al.  A hybrid SARIMA and support vector machines in forecasting the production values of the machinery industry in Taiwan , 2007, Expert Syst. Appl..

[30]  B. Eswara Reddy,et al.  A moving-average filter based hybrid ARIMA-ANN model for forecasting time series data , 2014, Appl. Soft Comput..

[31]  Ponnuthurai N. Suganthan,et al.  Ensemble incremental learning Random Vector Functional Link network for short-term electric load forecasting , 2018, Knowl. Based Syst..

[32]  Bijari Mehdi,et al.  WHICH METHODOLOGY IS BETTER FOR COMBINING LINEAR AND NONLINEAR MODELS FOR TIME SERIES FORECASTING , 2011 .

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

[34]  Gang Song,et al.  A novel double deep ELMs ensemble system for time series forecasting , 2017, Knowl. Based Syst..

[35]  Yi-Ming Wei,et al.  Carbon price forecasting with a novel hybrid ARIMA and least squares support vector machines methodology , 2013 .

[36]  Sven F. Crone,et al.  A study on the ability of Support Vector Regression and Neural Networks to Forecast Basic Time Series Patterns , 2006, IFIP AI.

[37]  Erasmo Cadenas,et al.  Wind speed forecasting in three different regions of Mexico, using a hybrid ARIMA–ANN model , 2010 .

[38]  George D. C. Cavalcanti,et al.  An Approach to Improve the Performance of PM Forecasters , 2015, PloS one.

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