Abstract




 
   

IJE TRANSACTIONS C: Aspects Vol. 29, No. 12 (December 2016) 1717-1725    Article in Press

downloaded Downloaded: 122   viewed Viewed: 1709

  A NONLINEAR AUTOREGRESSIVE MODEL WITH EXOGENOUS VARIABLES NEURAL NETWORK FOR STOCK MARKET TIMING: THE CANDLESTICK TECHNICAL ANALYSIS
 
E. Ahmadi, M. H. Abooie, M. Jasemi and Y. Zare Mehrjardi
 
( Received: February 19, 2015 – Accepted in Revised Form: September 30, 2016 )
 
 

Abstract    In this paper, the nonlinear autoregressive model with exogenous variables as a new neural network is used for timing of the stock markets on the basis of the technical analysis of Japanese Candlestick. In this model, the “nonlinear autoregressive model with exogenous variables” is an analyzer. For a more reliable comparison, here (like the literature) two approaches of Raw-based and Signal-based are devised to generate the input data of the model. The correct predictions percentages for periods of 1- 6 days with the total number of buy and sell signals are considered. The result proves that to some extent the approaches have similar performances while apparently, they are superior to a feed-forward static neural network. The created network is evaluated by the measure of Mean of Squared Error and the proposed model accuracy is calculated to be extremely high.

 

Keywords    Finance; Stock Market Forecasting; Technical Analysis; NARX Recurrent Neural Network; Levenberg–Marquardt Algorithm.

 

چکیده    در این مقاله، مدل اتورگرسیو غیرخطی با متغیرهای خارجی به عنوان یک شبکه عصبی جدید برای زمان بندی بازارهای سهام بر اساس تحلیل فنی شمعدان ژاپنی به کار رفته است. در مدل، اتورگرسیو غیرخطی با متغیرهای خارجی یک تحلیل گر است. اینجا (همانند ادبیات) دو رویکرد مبتنی بر دادهای خام و سیگنال برای ایجاد داده های ورودی تعبیه شده اند. درصد صحت پیش بینی برای دوره های زمانی 1-6 روزه با تعداد کل سیگنال های خرید و فروش در نظر گرفته شده است. نتایج اثبات می کند که رویکردها تا حدی عملکرد مشابه ای دارند در حالی که آن ها از شبکه عصبی پیشرو برتری دارند. شبکه ایجاد شده توسط معیار میانگین مربع خطا ارزیابی می شود و صحت مدل پیش بینی بسیار بالا محاسبه شده است.

References   

1.      Jasemi, M. and Kimiagari, A. M., "An investigation of model selection criteria for technical analysis of moving average", Journal of Industrial Engineering International,  Vol. 8, No. 1, (2012), 1-9.

2.      Chavarnakul, T. and Enke, D., "A hybrid stock trading system for intelligent technical analysis-based equivolume charting", Neurocomputing,  Vol. 72, No. 16, (2009), 3517-3528.

3.      Marshall, B. R., Young, M. R. and Rose, L. C., "Candlestick technical trading strategies: Can they create value for investors?", Journal of Banking & Finance,  Vol. 30, No. 8, (2006), 2303-2323.

4.      Kamo, T. and Dagli, C., "Hybrid approach to the japanese candlestick method for financial forecasting", Expert Systems with applications,  Vol. 36, No. 3, (2009), 5023-5030.

5.      Lee, K. and Jo, G., "Expert system for predicting stock market timing using a candlestick chart", Expert Systems with Applications,  Vol. 16, No. 4, (1999), 357-364.

6.      Xie, H., Zhao, X. and Wang, S., "A comprehensive look at the predictive information in japanese candlestick", Procedia Computer Science,  Vol. 9, (2012), 1219-1227.

7.      Lan, Q., Zhang, D. and Xiong, L., "Reversal pattern discovery in financial time series based on fuzzy candlestick lines", Systems Engineering Procedia,  Vol. 2, (2011), 182-190.

8.      Chen, Y., Mabu, S. and Hirasawa, K., "A model of portfolio optimization using time adapting genetic network programming", Computers & Operations Research,  Vol. 37, No. 10, (2010), 1697-1707.

9.      Crone, S. F. and Kourentzes, N., "Feature selection for time series prediction–a combined filter and wrapper approach for neural networks", Neurocomputing,  Vol. 73, No. 10, (2010), 1923-1936.

10.    Chang, P.-C., "A novel model by evolving partially connected neural network for stock price trend forecasting", Expert Systems with Applications,  Vol. 39, No. 1, (2012), 611-620.

11.    Atsalakis, G. S., Dimitrakakis, E. M. and Zopounidis, C. D., "Elliott wave theory and neuro-fuzzy systems, in stock market prediction: The wasp system", Expert Systems with Applications,  Vol. 38, No. 8, (2011), 9196-9206.

12.    Pradeep, J., Srinivasan, E. and Himavathi, S., "Neural network based   recognition   system   integrating  feature  extraction  and

classification for english handwritten", International Journal of Engineering-Transactions B: Applications,  Vol. 25, No. 2, (2012), 99-106.

13.    Lin, X., Yang, Z. and Song, Y., "Intelligent stock trading system based on improved technical analysis and echo state network", Expert Systems with applications,  Vol. 38, No. 9, (2011), 11347-11354.

14.    Lee, M.-C., "Using support vector machine with a hybrid feature selection method to the stock trend prediction", Expert Systems with Applications,  Vol. 36, No. 8, (2009), 10896-10904.

15.    Huang, S.-C. and Wu, T.-K., "Integrating ga-based time-scale feature extractions with svms for stock index forecasting", Expert Systems with Applications,  Vol. 35, No. 4, (2008), 2080-2088.

16.    O’Connor, N. and Madden, M. G., "A neural network approach to predicting stock exchange movements using external factors", Knowledge-Based Systems,  Vol. 19, No. 5, (2006), 371-378.

17.    Goel, A., "Ann based modeling for prediction of evaporation in reservoirs (research note)", International Journal of Engineering-Transactions A: Basics,  Vol. 22, No. 4, (2009), 351-358.

18.    Mahmoud, S., Lotfi, A. and Langensiepen, C., "Behavioural pattern identification and prediction in intelligent environments", Applied Soft Computing,  Vol. 13, No. 4, (2013), 1813-1822.

19.    Andalib, A. and Atry, F., "Multi-step ahead forecasts for electricity prices using narx: A new approach, a critical analysis of one-step ahead forecasts", Energy Conversion and Management,  Vol. 50, No. 3, (2009), 739-747.

20.    Pisoni, E., Farina, M., Carnevale, C. and Piroddi, L., "Forecasting peak air pollution levels using narx models", Engineering Applications of Artificial Intelligence,  Vol. 22, No. 4, (2009), 593-602.

21.    Kim, H.-j. and Shin, K.-s., "A hybrid approach based on neural networks and genetic algorithms for detecting temporal patterns in stock markets", Applied Soft Computing,  Vol. 7, No. 2, (2007), 569-576.

22.    Huo, F. and Poo, A.-N., "Nonlinear autoregressive network with exogenous inputs based contour error reduction in CNC machines", International Journal of Machine Tools and Manufacture,  Vol. 67, (2013), 45-52.

23.    Sahoo, H., Dash, P. and Rath, N., "Narx model based nonlinear dynamic system identification using low complexity neural networks and robust h∞ filter", Applied Soft Computing,  Vol. 13, No. 7, (2013), 3324-3334.

24.    Ardalani-Farsa, M. and Zolfaghari, S., "Chaotic time series prediction with residual analysis method using hybrid elman–narx neural networks", Neurocomputing,  Vol. 73, No. 13, (2010), 2540-2553.

25.    Soman, P. C., "An adaptive narx neural network approach for financial time series prediction", Rutgers University-Graduate School-New Brunswick,  (2008),

26.    Asadi, S., Hadavandi, E., Mehmanpazir, F. and Nakhostin, M. M., "Hybridization of evolutionary levenberg–marquardt neural networks and data pre-processing for stock market prediction", Knowledge-Based Systems,  Vol. 35, (2012), 245-258.

27.    Atsalakis, G. S. and Valavanis, K. P., "Surveying stock market forecasting techniques–part ii: Soft computing methods", Expert Systems with applications,  Vol. 36, No. 3, (2009), 5932-5941.

28.    Jasemi, M., Kimiagari, A. M. and Memariani, A., "A modern neural network model to do stock market timing on the basis of the ancient investment technique of japanese candlestick", Expert Systems with Applications,  Vol. 38, No. 4, (2011), 3884-3890.





International Journal of Engineering
E-mail: office@ije.ir
Web Site: http://www.ije.ir