Automatic time series forecasting using nonlinear autoregressive neural network model with exogenous input

This study aims to determine an automatic forecasting method of univariate time series, using the nonlinear autoregressive neural network model with exogenous input (NARX). In this automatic setting, users only need to supply the input of time series. Then, an automatic forecasting algorithm sets up the appropriate features, estimate the parameters in the model, and calculate forecasts, without the users’ intervention. The algorithm method used include preprocessing, tests for trends, and the application of first differences. The time series were tested for seasonality, and seasonal differences were obtained from a successful analysis. These series were also linearly scaled to [−1, +1]. The autoregressive lags and hidden neurons were further selected through the stepwise and optimization algorithms, respectively. The 20 NARX models were fitted with different random starting weights, and the forecasts were combined using the ensemble operator, in order to obtain the final product. This proposed method was applied to real data, and its performance was compared with several available automatic models in the literature. The forecasting accuracy was also measured by mean squared error (MSE) and mean absolute percent error (MAPE), and the results showed that the proposed method outperformed the other automatic models.

[1]  Sandra M. Guzmán,et al.  The Use of NARX Neural Networks to Forecast Daily Groundwater Levels , 2017, Water Resources Management.

[2]  Florentina Paraschiv,et al.  Extended forecast methods for day-ahead electricity spot prices applying artificial neural networks , 2016 .

[3]  John Kaiser Calautit,et al.  A review of artificial neural network models for ambient air pollution prediction , 2019, Environ. Model. Softw..

[4]  George D. Magoulas,et al.  New globally convergent training scheme based on the resilient propagation algorithm , 2005, Neurocomputing.

[5]  Malika Zazi,et al.  A Nonlinear TSNN Based Model of a Lead Acid Battery , 2018, Bulletin of Electrical Engineering and Informatics.

[6]  Sven F. Crone,et al.  Automatic time series analysis for electric load forecasting via support vector regression , 2019, Appl. Soft Comput..

[7]  Dedi Rosadi,et al.  Time Series Forecasting with Trend and Seasonal Patterns using NARX Network Ensembles , 2021, Mathematics and Statistics.

[8]  Rob J Hyndman,et al.  A state space framework for automatic forecasting using exponential smoothing methods , 2002 .

[9]  Rob J Hyndman,et al.  The admissible parameter space for exponential smoothing models , 2008 .

[10]  Tobi Delbrück,et al.  Training Deep Spiking Neural Networks Using Backpropagation , 2016, Front. Neurosci..

[11]  Muhammad Akram,et al.  New approach to Forecasting Agro-based statistical models , 2016, J. Stat. Theory Appl..

[12]  Apostolos Kotsialos,et al.  Traffic Flow Model Validation Using METANET, ADOL-C and RPROP , 2016 .

[13]  Josef Arlt,et al.  Automatic SARIMA modeling and forecast accuracy , 2019, Commun. Stat. Simul. Comput..

[14]  Nikolaos Kourentzes,et al.  The impact of special days in call arrivals forecasting: A neural network approach to modelling special days , 2018, Eur. J. Oper. Res..

[15]  Luis A. Aguirre,et al.  "Parallel Training Considered Harmful?": Comparing Series-Parallel and Parallel Feedforward Network Training , 2017, Neurocomputing.

[16]  M. Eladawy,et al.  Prediction of the true harmonic current contribution of nonlinear loads using NARX neural network , 2017, Alexandria Engineering Journal.

[17]  Sven F. Crone,et al.  A comparison of AdaBoost algorithms for time series forecast combination , 2016 .

[18]  Subanar,et al.  A Second Correlation Method for Multivariate Exchange Rates Forecasting , 2014 .

[19]  Tijani Lamhamdi,et al.  Lithium-Ion batteries modeling and state of charge estimation using Artificial Neural Network , 2019 .

[20]  Jackie Li,et al.  A Two-Population Extension of the Exponential Smoothing State Space Model with a Smoothing Penalisation Scheme , 2020, Risks.

[21]  Fotios Petropoulos,et al.  Another look at forecast selection and combination: Evidence from forecast pooling , 2019, International Journal of Production Economics.

[22]  Nikolaos Kourentzes,et al.  Distributions of forecasting errors of forecast combinations: Implications for inventory management , 2016 .

[23]  Sven F. Crone,et al.  Advances in forecasting with neural networks? Empirical evidence from the NN3 competition on time series prediction , 2011 .

[24]  D. Rosadi,et al.  SELECTION OF INPUT VARIABLES OF NONLINEAR AUTOREGRESSIVE NEURAL NETWORK MODEL FOR TIME SERIES DATA FORECASTING , 2020 .

[25]  Stefan Fritsch,et al.  neuralnet: Training of Neural Networks , 2010, R J..

[26]  Fadhlan Hafizhelmi Kamaru Zaman,et al.  Prediction of energy consumption using recurrent neural networks (RNN) and nonlinear autoregressive neural network with external input (NARX) , 2020 .

[27]  Suharjito,et al.  Waiting-Time Estimation in Bank Customer Queues using RPROP Neural Networks , 2018 .

[28]  Fotios Petropoulos,et al.  Forecast combinations for intermittent demand , 2015, J. Oper. Res. Soc..

[29]  Sven F. Crone,et al.  Cross-validation aggregation for combining autoregressive neural network forecasts , 2016 .

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

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

[32]  Hemerson Pistori,et al.  Long-term forecast of energy commodities price using machine learning , 2019, Energy.

[33]  Nikolaos Kourentzes,et al.  Feature selection for time series prediction - A combined filter and wrapper approach for neural networks , 2010, Neurocomputing.

[34]  Mashitah Che Razali,et al.  Modeling of submerged membrane filtration processes using recurrent artificial neural networks , 2020 .

[35]  Xiaozhe Wang,et al.  Characteristic-Based Clustering for Time Series Data , 2006, Data Mining and Knowledge Discovery.

[36]  Nikolaos Kourentzes,et al.  Automatic robust estimation for exponential smoothing: Perspectives from statistics and machine learning , 2020, Expert Syst. Appl..