Modelling and optimisation of effective hybridisation model for time-series data forecasting

Mergani Khairalla; Xu Ning; Nashat AL-Jallad

Modelling and optimisation of effective hybridisation model for time-series data forecasting

View Fulltext

Author(s): Mergani Khairalla^{1, 2} ; Xu Ning¹ ; Nashat AL-Jallad¹
- Affiliations: 1: School of Computer and Science and Technology , Wuhan University of Technology , Wuhan 430070 , People's Republic of China ;
  2: School of Science and Technology , Nile Valley University , Atbara , Sudan
Source: Volume 2018, Issue 2, February 2018, p. 117 – 122
DOI: 10.1049/joe.2017.0337 , Online ISSN 2051-3305

This is an open access article published by the IET under the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0/)

Received 09/08/2017, Accepted 18/12/2017, Published 15/01/2018

Financial time-series data have non-linear and uncertain behavior which changes across the time. Therefore, the need to solve non-linear, time-variant problems has been growing rapidly. Traditional models such as statistical and data mining approach unable to cope with these issues. The main objective of this study to combine forecasts from the autoregressive integrated moving average model, exponential (EXP) model, and the multi-layers perceptron (MLP) in a novel hybrid model. The analysis was based on financial data of Sudanese pound/EURO exchange rate in Sudan. In this case, simple additive combination and weight combination methods are used in combining linear and non-linear models to produce hybrid forecast. Comparison between benchmark models and hybrid indicates that the hybrid model offers more accurate forecasts with reduced mean-absolute percentage error of around 0.82% for all models over all forecasting horizons. Moreover, the results recommend that the non-linear method can be applicable to an alternate to linear combining methods to accomplish better forecasting accuracy. On the basis of the results of this study, the authors can conclude that further experiments to estimate the weight of the combination methods and more models essential to be surveyed so as to explore innovative concerns in series prediction.

References

1. 1)
  - 19. Faruk, D.Ö.: ‘A hybrid neural network and ARIMA model for water quality time series prediction’, Eng. Appl. Artif. Intell., 2010, 23, (4), pp. 586–594 (doi: 10.1016/j.engappai.2009.09.015).
2. 2)
  - 6. Zhang, Y., Wu, L.: ‘Stock market prediction of S&P 500 via combination of improved BCO approach and BP neural network’, Expert Syst. Appl., 2009, 36, (5), pp. 8849–8854 (doi: 10.1016/j.eswa.2008.11.028).
3. 3)
  - 16. Aladag, C.H., Egrioglu, E., Kadilar, C.: ‘Forecasting nonlinear time series with a hybrid methodology’, Appl. Math. Lett., 2009, 22, (9), pp. 1467–1470 (doi: 10.1016/j.aml.2009.02.006).
4. 4)
  - 7. Merh, N., Saxena, V.P., Pardasani, K.R.: ‘A comparison between hybrid approaches of ANN and ARIMA for Indian stock trend forecasting’, Bus. Intell. J., 2010, 3, (2), pp. 23–43.
5. 5)
  - 5. Shadbolt, J.: ‘Neural networks and the financial markets: predicting, combining, and portfolio optimisation’ (Springer Science & Business Media, Berlin, Germany, 2002).
6. 6)
  - 1. Ariyo, A.A., Adewumi, A.O., Ayo, C.K.: ‘Stock price prediction using the ARIMA model’. 2014 UKSim-AMSS 16th Int. Conf. IEEE Computer Modelling and Simulation (UKSim), 2014.
7. 7)
  - 11. Humphrey, G.B., Gibbs, M.S., Dandy, G.C., et al: ‘A hybrid approach to monthly stream flow forecasting: integrating hydrological model outputs into a Bayesian artificial neural network’, J. Hydrol., 2016, 540, pp. 623–640 (doi: 10.1016/j.jhydrol.2016.06.026).
8. 8)
  - 8. Guresen, E., Kayakutlu, G., Daim, T.U.: ‘Using artificial neural network models in stock market index prediction’, Expert Syst. Appl., 2011, 38, (8), pp. 10389–10397 (doi: 10.1016/j.eswa.2011.02.068).
9. 9)
  - 14. Sallehuddin, R., Shamsuddin, S.M.H., Hashim, S.Z.M., et al: ‘Forecasting time series data using hybrid grey relational artificial neural network and auto regressive integrated moving average model’, Neural Netw. World, 2007, 17, (6), p. 573.
10. 10)
  - 20. Vahdani, B., Mousavi, S.M., Hashemi, H., et al: ‘A new hybrid model based on least squares support vector machine for project selection problem in construction industry’, Arab. J. Sci. Eng., 2014, 39, (5), pp. 4301–4314 (doi: 10.1007/s13369-014-1032-8).
11. 11)
  - 10. Babu, C.N., Reddy, B.E.: ‘A moving-average filter based hybrid ARIMA–ANN model for forecasting time series data’, Appl. Soft Comput., 2014, 23, pp. 27–38 (doi: 10.1016/j.asoc.2014.05.028).
12. 12)
  - 15. Fatima, S., Hussain, G.: ‘Statistical models of KSE100 index using hybrid financial systems’, Neurocomputing, 2008, 71, (13), pp. 2742–2746 (doi: 10.1016/j.neucom.2007.11.044).
13. 13)
  - 12. Dai, W., Wu, J.-Y., Lu, C.-J.: ‘Combining nonlinear independent component analysis and neural network for the prediction of Asian stock market indexes’, Expert Syst. Appl., 2012, 39, (4), pp. 4444–4452 (doi: 10.1016/j.eswa.2011.09.145).
14. 14)
  - 18. Koutroumanidis, T., Ioannou, K., Arabatzis, G.: ‘Predicting fuel wood prices in Greece with the use of ARIMA models, artificial neural networks and a hybrid ARIMA–ANN model’, Energy Policy, 2009, 37, (9), pp. 3627–3634 (doi: 10.1016/j.enpol.2009.04.024).
15. 15)
  - 22. Chaâbane, N.: ‘A hybrid ARFIMA and neural network model for electricity price prediction’, Int. J. Electr. Power Energy Syst., 2014, 55, pp. 187–194 (doi: 10.1016/j.ijepes.2013.09.004).
16. 16)
  - 9. Hua, X., Zhang, D., Leung, S.C.: ‘Exchange rate prediction through ANN based on kernel regression’. 2010 Third Int. Conf. IEEE Business Intelligence and Financial Engineering (BIFE), 2010.
17. 17)
  - 3. Zhang, G.P.: ‘Neural networks in business forecasting’ (IGI Global, USA, 2004).
18. 18)
  - 4. Zhang, G.P.: ‘Time series forecasting using a hybrid ARIMA and neural network model’, Neurocomputing, 2003, 50, pp. 159–175 (doi: 10.1016/S0925-2312(01)00702-0).
19. 19)
  - 17. Sadaei, H.J., Enayatifar, R., Guimarães, F.G., et al: ‘Combining ARFIMA models and fuzzy time series for the forecast of long memory time series’, Neurocomputing, 2016, 175, pp. 782–796 (doi: 10.1016/j.neucom.2015.10.079).
20. 20)
  - 13. Taskaya-Temizel, T., Casey, M.C.: ‘A comparative study of autoregressive neural network hybrids’, Neural Netw., 2005, 18, (5), pp. 781–789 (doi: 10.1016/j.neunet.2005.06.003).
21. 21)
  - 2. Box, G.E., Jenkins, G.M., Reinsel, G.C., et al: ‘Time series analysis: forecasting and control’ (John Wiley & Sons, Hoboken, NJ, USA, 2015).
22. 22)
  - 21. Bergmeir, C., Benítez, J.M.: ‘On the use of cross-validation for time series predictor evaluation’, Inf. Sci., 2012, 191, pp. 192–213 (doi: 10.1016/j.ins.2011.12.028).

Login

Not registered yet?

Share

Tools

Login to add to favourites

Key

Modelling and optimisation of effective hybridisation model for time-series data forecasting

References

Related content