Document Type : Original Article


Department of Industrial and systems Engineering, Isfahan University of Technology, Isfahan, Iran.


With the increasing importance of forecasting with the utmost degree of accuracy, utilizing hybrid frameworks become a must for obtaining more accurate and more reliable forecasting results. Series hybrid methodology is one of the most widely-used hybrid approaches that has encountered a great amount of popularity in the literature of time series forecasting and has been applied successfully in a wide variety of domains. In such hybrid methods is assumed that there is an additive relationship among different components of time series. Thus, based on this assumption, various individual models can apply separately on decomposed components, and the final forecast can be obtained. However, developed series hybrid models in the literature are constructed based on the decomposing time series into linear and nonlinear parts and generating linear-nonlinear modeling order for decomposed parts. Another assumption considered in the traditional series model is assigning equal weights to each model used for modeling linear and nonlinear components. Thus, contrary to traditional series hybrid models, to improve the performance of series hybrid models, these two basic assumptions have been violated in this paper. This study aims to propose a novel weighted MLP-ARIMA model filling the gap of series hybrid models by changing the order of sequence modeling and assigning weight for each component. Firstly, the modeling order is changed to nonlinear-linear, and then Multi-Layer Perceptron Neural Network (MLPNN) -Auto-Regressive Integrated Moving Average(ARIMA) models are employed to model and process nonlinear and linear components respectively. Secondly, each model's weights are computed by the Ordinary Least Square (OLS) weighting algorithm. Thus, in this paper, a novel improved weighted MLP-ARIMA series hybrid model is proposed for time series forecasting. The real-world benchmark data sets, including Wolf's sunspot data, the Canadian lynx data, and the British pound/US dollar exchange rate data, are elected to verify the effectiveness of the proposed weighted MLP-ARIMA series hybrid model. The simulation results revealed that the weighted MLP-ARIMA model could obtain superior performance compared to ARIMA-MLP, MLP-ARIMA, as well as the ARIMA and MLPNN individual models. The proposed hybrid model can be an effective alternative to improve forecasting accuracy obtained by traditional series hybrid methods.


Babu, CN., and Sure, P., (2016). "Partitioning and interpolation based hybrid ARIMA–ANN model for time series forecasting", Sādhanā, Vol. 41, pp. 695–706.
Box ,P., and Jenkins, G.M., (1976). Time Series Analysis: Forecasting and Control, Holden-day Inc., San Francisco, CA.
Chakraborty, T., Chattopadhyay, and S., Ghosh, I., (2019). "Forecasting dengue epidemics using a hybrid methodology", Physica A, Vol. 527.
Clemen, R. T., (1989). “Combining forecasts: A review and annotated bibliography”, International Journal of Forecasting, Vol. 5, pp. 559-583.
Granger, CWJ., and Ramanathan, R., (1984). "Improved Methods of Combining Forecasts", Journal of Forecasting, Vol. 3, pp. 197–204.
Hajirahimi, Z., and Khashei, M., (2016). "Improving the performance of financial forecasting using different combination architectures of ARIMA and ANN models", Journal of Industrial Engineering and Management Studies, Vol. 3, pp. 17-32.
Hajirahimi, Z., and Khashei, M., (2019). "Weighted sequential hybrid approaches for time series forecasting", Physica A, Vol. 531, pp. 1-14.
Hipel, K.W., and McLeod, A.I., (1994). Time Series Modeling of Water Resources and Environmental Systems, Amsterdam, Elsevier.
Hu, Y., Li, J., Hong, M., Ren, Jingzheng., Lin, Ruojue., Liu, Yue., Liu, M., and Man,Yi., (2019). "Short term electric load forecasting model and its verification for process industrial enterprises based on hybrid GA-PSO-BPNN algorithm -A case study of papermaking process", Energy, Vol. 170, pp. 1215-1227.
Iravani, M., Bashirzadeh, R., and Tarokh, M.J., (2020). "Developing an urban congestion pricing model by considering sustainability improvement and using a multi-objective optimization approach", Journal of Industrial Engineering and Management Studies, Vol. 7, pp. 56-76.
Khashei, M., and Bijari, M., (2010). "An artificial neural network (p, d ,q) model for timeseries forecasting", Expert Systems with Applications, Vol. 37, pp. 479–489.
Khashei, M., and Bijari, M., (2012). "A new class of hybrid models for time series forecasting", Expert System with Application, Vol. 39, pp. 4344–4357.
Kumar Chandar, S., (2019). “Fusion model of wavelet transform and adaptive neuro fuzzy inference system for stock market prediction”, Journal of Ambient Intelligence and Humanized Computing, pp.1-9.
Lan, H., Zhang, Ch., Hong, Ying-Yi., He, Y., and Wen, Shuli., (2019). "Day-ahead spatiotemporal solar irradiation forecasting using frequency based hybrid principal component analysis and neural network", Applied Energy, Vol. 247, pp. 389–402.
Liu, Z., Wang, X., Zhang, Q., and Huang, Ch., (2019). "Empirical mode decomposition based hybrid ensemble model for electrical energy consumption forecasting of the cement grinding process", Measurement, Vol. 138, pp. 314–324.
Meese, R.A., and Rogoff, K., (1983). "Empirical exchange rate models of the seventies: do they/t out of samples? ", Journal of International Economics, Vol. 14, pp. 3–24.
Moeeni, H., Bonakdari, H., and Ebtehaj, Isa., (2017). "Monthly reservoir inflow forecasting using a new hybrid SARIMA genetic programming approach", Journal of Earth System Science, Vol. 126, pp. 1–13.
Mukaram, MZ., and Yusof, F., (2017). "Solar radiation forecast using hybrid SARIMA and ANN model: A case study at several locations in Peninsular Malaysia", Malaysian Journal of Fundamental and Applied Sciences, pp. 346-350.
Naveena, K., Singh, Subedar., Rathod, Santosha., and Singh, Abhishek., (2017). "Hybrid ARIMA-ANN Modeling for Forecasting the Price of Robusta Coffee in India", International Journal of Current Microbiology and Applied Sciences, Vol.7, pp. 1721-1726.
Singh, P. K., Singh, Nitin., and Negi, Richa., (2019). "Wind Power Forecasting Using Hybrid ARIMA-ANN Technique", Ambient Communications and Computer Systems, pp. 209-220.
Stone, L., He, D., (2007). "Chaotic oscillations and cycles in multi-trophic ecological systems", Journal of Theoretical Biology, Vol. 248, pp. 382–390.
Suhermi, N ., Prastyo, DD., and Ali, B., (2018). "Roll motion prediction using a hybrid deep learning and ARIMA model", Procedia Computer Science, Vol. 144, pp. 251–258.
Timermann, A., (2006). Forecast Combinations, in Handbook of Economic Forecasting, Vol. 1, eds. G. Elliott, C. Granger, and A. Timmermann, Ams-terdam: Elsevier, pp. 135–196.
Velasco, LCP., Polestico, DLL., Macasieb, GPO., Reyes, MBV., and Vasquez, Jr. FB., (2018). "Load forecasting using autoregressive integrated moving average and artificial neural network", International Journal of Advanced Computer Science and Applications, Vol. 9, pp. 23–39.
Yuan, X., Chen, Ch., Jiang, M., and Yuan, Yanbin., (2019). "Prediction interval of wind power using parameter optimized Beta distribution based LSTM model", Applied Soft Computing Journal, Vol. 82.
Zaree, M., Kamranrad, R., Zaree, M., and Emami, I., (2020). "Project scheduling optimization for contractor’s Net present value maximization using meta-heuristic algorithms: A case study", Journal of Industrial Engineering and Management Studies, Vol. 7, pp. 36-55.
Zhang, G. P., (2003). "Time series forecasting using a hybrid ARIMA and neural network model", Neurocomputing, Vol. 50, pp. 159–175.
Zhang, G., Patuwo, BE., and Hu, M., (1998). "Forecasting with artificial neural networks: the state of the art", International Journal of Forecasting, Vol. 14, pp. 35–62.
Zhang, Y., Chen, B., Pan, G., and Zhao, Y., (2019). "A novel hybrid model based on VMD-WT and PCA-BP-RBF neural network for short-term wind speed forecasting", Energy Conversion and Management, Vol. 195, pp. 180–197.
Zhang, Y., Luo, L., Yang, J., Liu, D., Kong, R, and Feng, Y., (2018). "A hybrid ARIMA-SVR approach for forecasting emergency patient flow", Journal of Ambient Intelligence and Humanized Computing, Vol. 10, pp. 3315–3323.