Predicting Nike Company Stock Price in Stock Market Using NARX Artificial Neural Network Method

Document Type : Original Article


1 Assistant Professor of Sport Management University of Tabriz, Tabriz, Iran

2 M.A. of Sport Management University of Tabriz, Tabriz, Iran

3 Assisstant Professor of Sport Management, Faculty of Humanities, Bozorgmehr, University of Qaenat



One of the biggest challenges for the companies in the stock market is to predict the trend. This research aims to study the price action of the Nike stock trend in the NYSE. The price data was gathered from NYSE in a certain time period, and other variables such as Volume, Crude Oil Prices Brent – Europe, Effective Federal Funds Rate, Gold Fixing Price, etc. those who are recognized as influential variables on stock price, are gathered from The World Bank data source. We used one Artificial Neural Networks models to analyze the data for predicting time series (NARX). After correcting the objections such as invalid data's, the Error Autocorrelation gets 95% desire, and with 0.36 MSE error, we get the approval and the model adequate to predict the trend. With these settings, the input vectors and target vectors will be randomly divided into three sets, and then the model tries to learn from the first part of the data and then test it on the test data, and at the end, the last 24-month data predicted from the model and then compared with the central values. The data comparison showed a high overlap near 95%, which proved the adequacy of the model in predicting the price trend of Nike company.


  • Anderson, D., & McNeill, G. (1992). Artificial neural network technology. Kaman Sciences Corporation, 258(6), 1-83.
  • Atsalakis, G. S., & Valavanis, K. P. (2009). Surveying stock market forecasting techniques–Part II: Soft computing methods. Expert systems with applications, 36(3), 5932-5941.
  • Averchenko, D., & Aldyrev, A. (2018). Applying Neural Networks for Modeling of Financial Assets. In Fractal Approaches for Modeling Financial Assets and Predicting Crises (pp. 172-204): IGI Global.
  • BALVERS, R. J., COSIMANO, T. F., & MCDONALD, B. (1990). Predicting Stock Returns in an Efficient Market. The Journal of Finance, 45(4), 1109-1128. doi:
  • Bennett, P., & Wei, L. (2006). Market structure, fragmentation, and market quality. Journal of Financial Markets, 9(1), 49-78.
  • Beygi, S. A. K., & Abdolvand, N. (2017). Stock Price Prediction Modeling Using Artificial Neural Network Approach and Imperialist Competitive Algorithm Based On Chaos Theory. Journal of Financial Management Strategy, 5(18).
  • Chen, N.-F., Roll, R., & Ross, S. A. (1986). Economic forces and the stock market. Journal of business, 383-403.
  • Chortareas, G., & Noikokyris, E. (2014). Oil shocks, stock market prices, and the US dividend yield decomposition. International Review of Economics & Finance, 29, 639-649.
  • Fathian, M., & Kia, A. (2012). Exchange rate prediction with a multilayer perceptron neural network using a gold price as an external factor. Management Science Letters, 2, 561-570.
  • Flynn, P. (2015). Nike Marketing Strategy: A Company to Imitate.
  • Ghobadi, M., & Sharifi, E. (2015). Relationship Between Oil Prices Shocks And Stock Price Indexes In Iran. Фінансовий простір(3 (19)), 92-101.
  • Hellstrom, T., & Holmstrom, K. (1998). Predicting the stock market. Unpublished Thesis, Malardalen University, Department of Mathematics and Physics, Vasteras, Sweden.
  • Hsieh, T.-J., Hsiao, H.-F., & Yeh, W.-C. (2011). Forecasting stock markets using wavelet transforms and recurrent neural networks: An integrated system based on artificial bee colony algorithm. Applied soft computing, 11(2), 2510-2525.
  • Kuntomah, C. (2013). Effect of Exchange Rates Volatility on Stock Prices: Evidence From The Ghana Stock Exchange.
  • Lewis, N. (2017). Neural Networks for Time Series Forecasting with R. In CreateSpace Independent Publishing Platform, ISBN-10.

Na, S. H., & Sohn, S. Y. (2011). Forecasting changes in Korea composite