International Journal of Nonlinear Analysis and Applications

Designing a model for financial forecasting using the integration of neural networks, Box Jenkins and Holt Winters methodology

Articles in Press

Document Type : Research Paper

Authors

Department of Management, Central Tehran Branch, Islamic Azad University, Tehran, Iran.

10.22075/ijnaa.2022.27996.3776

Abstract

The present study designs a model for financial forecasting by integrating neural networks. This retrospective comparative study uses the average price data of OPEC oil from 2003 to 2022 to forecast the period from June 2022 to May 2024. To this end, two time-series models (Box-Jenkins and Holt-Winters) were examined, which in the second stage were incorporated into a hybrid model based on artificial neural networks. The neural network model was developed using Matlab, and the Box-Jenkins time-series model was constructed using SPSS and Eviews software. Based on the results of the error analysis of the Box-Jenkins methodology, among the time series processes ARIMA(5,1,5), ARIMA(4,1,5), ARIMA(3,1,5), and ARIMA(5,1,3), the models demonstrated the best accuracy with MSE values of 61.86, 63.21, 63.29, and 63.62, respectively. The accuracy of the Holt-Winters method was not suitable for time-series forecasting due to the nature of the data. Therefore, the best artificial neural network was designed for combining forecasting methods. This neural network included an input layer with 5 neurons, a hidden layer with 5 neurons, and a single-neuron output layer. The network was trained using the Levenberg-Marquardt algorithm and employed a linear sigmoid activation function. The results indicated that the designed hybrid neural network significantly improved the accuracy of the forecasting methods and enhanced the MSE, MAPE, AIC, and BIC indices.

Keywords

[1] L.-H. Chen and T.-Y. Guo, Forecasting financial crises for an enterprise by using the Grey Markov forecasting model, Qual. Quant. 45 (2011), no. 4, 911–922.
[2] C.-W.J. Chiu, H. Mumtaz and G. Pinter, Forecasting with VAR models: Fat tails and stochastic volatility, Int. J. Forecast. 33 (2017), no. 4, 1124–1143.
[3] H.B. Ghassan and H.R. AlHajhoj, Long run dynamic volatilities between OPEC and non-OPEC crude oil prices, Appl. Energy 169 (2016), 384–394.
[4] K. Hezhabr Kiani, E. Gholami, and J. Nobakht, Estimation of the optimal rate of value added tax using the Diamond model, Quart. J. Econ. Res. 32 (2012), no. 2, 11–22.
[5] R.J. Hyndman and G. Athanasopoulos, Forecasting: Principles and practice, Monash University, Australia, 2019.
[6] W. Kristjanpoller and M.C. Minutolo, Forecasting volatility of oil price using an artificial neural network-GARCH model, Expert Syst. Appl. 65 (2016), 233–241.
[7] Z. Li, J.M. Rose and D.A. Hensher, Forecasting automobile petrol demand in Australia: An evaluation of empirical models, Transport. Res. Part A: Policy Practice 44 (2010), no. 1, 16–38.
[8] W.S. McCulloch and W. Pitts, A logical calculus of the ideas immanent in nervous activity, Bull. Math. Biophys. 5 (1943), 115–133.
[9] M.R. Omidi, N. Omidi, H.A. Asgari and H. Meftahi, Mathematical analysis of traffic accidents using gray and rotational models, Traffic Manag. Stud. 42 (2021), no. 11, 97–112.
[10] H. Poursalimi and R. Shirzadi, Developments in the relations between Iran and Saudi Arabia and its impact on the oil market, J. Explor. Prod. Oil Gas 2015 (2015), no. 141, 40–44. [In Persian]
[11] R. Prasad, R.C. Deo, Y. Li, and T. Maraseni, Input selection and performance optimization of ANN-based stream-flow forecasts in the drought-prone Murray Darling Basin region using IIS and MODWT algorithm, Atmosph. Res. 197 (2017), 42–63.
[12] K. Shahbazi and S. Salimian, Oil price forecasting using meta-analysis method, Energy Econ. Quart. 2014 (2014), no. 29, 67–93.
[13] B. Sivaneasan, C.Y. Yu and K.P. Goh, Solar forecasting using ANN with fuzzy logic pre-processing, Energy Procedia 143 (2017), 727–732.
[14] H. Sohrabi Vafa, F. Nouri and M. Ebadi, Energy demand prediction by using neural network based on particle swarm optimization, Iran. Energy J. 16 (2019), no. 3, 6.
[15] Q.-F. Tan, X.-H. Lei, X. Wang, H. Wang, X. Wen, Y. Ji, and A.-Q. Kang, An adaptive middle and long-term runoff forecast model using EEMD-ANN hybrid approach, J. Hydrol. 567 (2018), 767–780.
[16] C. Troise, D.Matricano, E. Candelo, and M. Sorrentino, Entrepreneurship and fintech development: comparing reward and equity crowdfunding, Meas. Bus. Excell. 26 (2021), no. 1, 52–63.
[17] M.H. Vatter, OPEC’s Risk premia and volatility in oil prices, Int. Adv. Econ. Res. 25 (2019), no. 2, 165–175.
[18] X. Wang and M. Meng, A hybrid neural network and ARIMA model for energy consumption forcasting, J. Comput. 7 (2012), no. 5, 1184–1190.
[19] R. Wongsathan and S. Chankham, Improvement on PM-10 forecast by using hybrid ARIMAX and neural networks model for the summer season in Chiang Mai, Proc. Comput. Sci. 86 (2016), 277–280.
[20] Y. Xue, T. Teng, F. Dang, Z. Ma, S. Wang, and H. Xue, Productivity analysis of fractured wells in reservoir of hydrogen and carbon based on dual-porosity medium model, Int. J. Hydrog. Energy 45 (2020), no. 39, 20240–20249.
[21] M.G. Yousefi, T. Mohammadi, and N. Maarrefzadeh, Forecasting the amount of crude oil demand in Iran using artificial neural networks (ANN) and ARMAX model, Iran. Energy Econ. Quart. 2 (2012), no. 7, 147–170.
[22] W. Zhao, J. Wang, and H. Lu, Combining forecasts of electricity consumption in China with time-varying weights updated by a high-order Markov chain model, Omega 45 (2014), 80–91.
[23] S.H. Zolnoor and S. Mateen, Optimizing Iran’s oil production path: A dynamic planning optimal control model, Plan. Budget. Quart. 20 (2014), no. 4.
International Journal of Nonlinear Analysis and Applications

Articles in Press, Corrected Proof
Available Online from 13 November 2024
  • Receive Date: 03 June 2022
  • Accept Date: 18 August 2022