Abstract
Supplying industrial firms with an accurate method of forecasting the production value of the mechanical industry to facilitate decision makers in precise planning is highly desirable. Numerous methods, including the autoregressive integrated-moving average (ARIMA) model and artificial neural networks can make accurate forecasts based on historical data. The seasonal ARIMA (SARIMA) model and artificial neural networks can also handle data involving trends and seasonality. Although neural networks can make predictions, deciding the most appropriate input data, network structure and learning parameters are difficult. Therefore, this article presents a hybrid forecasting method that combines the SARIMA model and neural networks with genetic algorithms. Analytical results generated by the SARIMA model are inputted as the input data of a neural network. Subsequently, the number of neurons in the hidden layer and the number of learning parameters of the neural network architecture are globally optimized using genetic algorithms. This model is subsequently adopted to forecast seasonal time series data of the production value of the mechanical industry in Taiwan. The results presented here provide a valuable reference for decision makers in industry.
Similar content being viewed by others
References
Azoff EM (1994) Neural network time series prediction of financial market. Wiley, London
Box GEP, Jenkins GM (1976) Time series analysis prediction and control. Holden-Day, San Francisco
Tang Z, Chrys DA, Fishwick PA (1991) Time series forecasting using neural net works vs. Box-Jenkins methodology. Simulation 57(5):303–331. doi:10.1177/003754979105700508
Maier HR, Dandy GC (1996) Neural network models for prediction univariate time series. Neural Netw World 6(5):747–772
Hibon M, Evgeniou TA (2005) Simple procedure for reliability of repairable systems. Int J Forecast 21:15–24. doi:10.1016/j.ijforecast.2004.05.002
Rumelhart DE, Hinton GE, Williams RJ (1986) Parallel distributed processing, explorations in the microstructure of cognition, 1, foundations. MIT Press, Cambridge
Luvai M, Mahmound W (2000) Predictable variation and profitable trading of US equities: a trading simulation using neural networks. Comput Oper Res 27:1111–1129. doi:10.1016/S0305-0548(99)00148-3
Yu L, Wang S, Lai KK (2005) A novel nonlinear forecasting model incorporating GLAR and ANN for foreign exchange rate. Comput Oper Res 32:2523–2541. doi:10.1016/j.cor.2004.06.024
Wedding II, Cios KJ (1996) Time series forecasting by combing RBF networks, certainty factors, and the Box-Jenkins model. Neurocomputing 101:49–168
Voort MVD, Dougherty M, Watson S (1996) Combing Kohonen maps with ARIMA time series models to forecast traffic flow Transportation Research Part C. Emerg Technol 4:307–318
Juliana Y (2002) A comparison of neural networks with time series models for prediction returns on a stock market index. In: IEA/AIE 2002, LNAI 2358, pp 25–35
Zhang GP (2003) Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing 50:159–175. doi:10.1016/S0925-2312(01)00702-0
Pai PF, Liu CS (2005) A hybrid ARIMA model and support vector machines neural network model in stock price forecasting. Omega 33:497–505. doi:10.1016/j.omega.2004.07.024
Tong LI, Liang YH (2005) Prediction field failure data for repairable systems using neural networks and SARIMA model. Int J Qual Reliab Manage 22(4):410–420. doi:10.1108/02656710510591237
Holland J (1975) Adaption in natural and artificial systems. University of Michigan Press, Ann Arbor
Adeli H, Hung S (1995) Machine learning: neural networks, genetic algorithms, fuzzy systems. Wiley, New York
Chen SH (2002) Genetic algorithms and genetic programming in computational finance. Kluwer, Dordrecht
Sexton RS, Alidaee B, Dorsey RE, Johnson JD (1998) Global optimization for artificial neural networks: a tabu search application. Eur J Oper Res 106(2/3):570–584. doi:10.1016/S0377-2217(97)00292-0
Sexton RS, Alidaee B, Dorsey RE, Johnson JD (1998) Toward global optimization of neural networks: a comparison of the genetic algorithm and backpropagation. Decis Support Syst 22(2):171–185. doi:10.1016/S0167-9236(97)00040-7
Whitley D, Starkweather T, Bogart C (1990) Genetic algorithm and neural networks: optimizing connections and connectivity. Parallel Comput 14:280–311. doi:10.1016/0167-8191(90)90086-O
Bullinaria JA (2007) Using evolution to improve the neural network learning: pitfall and solutions. Neural Comput 16:209–226. doi:10.1007/s00521-007-0087-9
Kai F, Xu W (1997) Training neural network with genetic algorithms for forecasting the stock price index. In: Proceeding of the 1997 IEEE international conference on intelligent proceeding systems, pp 401–403
Shazly MR, Shazly HE (1999) Forecasting exchange rates using a genetically evolved neural network architecture. Int Rev Financ Anal 8:67–82. doi:10.1016/S1057-5219(99)00006-X
Kim KJ, Ham I (2000) Genetic algorithms approach to feature discretization in artificial neural networks for the prediction of stock price index. Expert Syst Appl 19:125–132. doi:10.1016/S0957-4174(00)00027-0
Liu Y, Yao X (2001) Evolving neural networks for Hang Seng Stock Index Forecast, In: Proceedings of the 2001 congress on evolutionary computation, pp 256–160
Paul K, Hoh P, Daohua M, Weidong L (2001) Neural network with genetically evolved algorithms for stocks prediction. Asia-Pacific J Oper Res Singapore 18:103–107
Giuliano A, Andrea M, Fabio R (2001) Stock market prediction by a mixture of genetic-neural experts. Int J Pattern Recognit Artif Intell 16(5):501–526
Versace M, Bhatt R, Hinds O, Shiffer M (2004) Predicting the exchange traded fund DIA with a combination of genetic algorithms and neural networks. Expert Syst Appl 27:417–425. doi:10.1016/j.eswa.2004.05.018
Liang YH (2007) Evolutionary neural network modeling for forecasting the field failure data of repairable Systems. Expert Syst Appl 33(4):1090–1096. doi:10.1016/j.eswa.2006.08.032
Makridakis SR, Andersen A, Carbone R, Fildes R, Hibon M, Lewandowski J, Newton R, Winkler R (1982) The accuracy of extrapolation (time series) methods: results of a forecasting competition. J Forecast 1:111–153. doi:10.1002/for.3980010202
Terui N, Dijk HK (2002) Combined forecasts from linear and nonlinear time series models. Int J Forecast 18:421–438. doi:10.1016/S0169-2070(01)00120-0
Fang Y (2003) Forecasting combination and encompassing tests. Int J Forecast 19:87–94. doi:10.1016/S0169-2070(01)00121-2
Principe JC, Euliano NR, Lefebvre WC (2000) Neural and adaptive systems: fundamentals through simulations. Wiley, New York
Cao Q, Leggio KB, Schniederjans MJ (2005) A comparison between Fama and French’s model and artificial neural networks in predicting the Chinese stock market. Comput Oper Res 32:2499–2512. doi:10.1016/j.cor.2004.03.015
Delurgio SA (1999) Forecasting principles and applications. Irwin/McGraw-Hill, New York
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Liang, YH. Combining seasonal time series ARIMA method and neural networks with genetic algorithms for predicting the production value of the mechanical industry in Taiwan. Neural Comput & Applic 18, 833–841 (2009). https://doi.org/10.1007/s00521-008-0216-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-008-0216-0