Open Access Open Access  Restricted Access Subscription or Fee Access

Neural Network and PLS Regression Models for Predicting Stock Prices

K. V. Sujatha, S. Meenakshi Sundaram

Abstract


Stock Index prediction has gained importance in recent times due to its commercial application and the nature of the data explored. The noisy environment of the data attracts many researchers to explore it. Common statistical models for time series data require the normality assumptions. But for the highly volatile stock data the normality conditions are violated and hence nonparametric models are essential for the analysis. In this study Multiple Linear Regression, Partial Least Square Regression and computational Neural Network models are proposed to explore stock market tendency and predict the daily closing prices using thirteen variables. Prediction ability of the models are measured using standard error values. Sum of Square error and Relative error are used to find the best Multilayer Perceptron Model. The models are compared based on MAPE and RMSE values. The results revealed that Nonparametric Partial Least Square Regression Model is better in predicting the daily closing prices than the classical Multiple Linear Regression and computational Multilayer Perceptron.

Keywords


Multivariate Normality, PLS Regression, Prediction, Root Mean Square Error

Full Text:

PDF

References


D. R. Cox and N. J. H. Small, “Testing Multivariate Normality”, Biometrika, Volume 65, pp. 263-272.

D. R. Cox and Wermuth, “Tests of linearity, Multivariate Normality and the adequacy of linear scores”, Applied Statistics, Volume 43, pp. 347-355.

J. Galindo, “ A framework for comparative analysis of statistical and machine learning methods: An application to the black scholes option pricing equations”, Techincal report Banco de Mexico, Mexico, DF,04930, 1998.

J. M. Hutchinson , Loaw and T. Poggio, “A nonparametic approach to pricing and hedging derivative securities via learning networks”,Journal of Finance, 1994, Volume 49, pp. 851–889.

J. Yao and C. L. Tan, “A case study on neural networks to perform technical forecasting of forex”, Neurocomputing , Volume 34, 2000, pp. 79-98.

K. V. Mardia, “Measures of multivariate Skewness and Kurtosis with applications”, Biometrika, Volume 57, 1970, pp. 519-530.

K. V. Mardia, “Tests of univariate and Multivariate Normality”, In Krishnaiah P.R. (ed.), Hand book of Statistics, Volume 1, Chapter 9, Amsterdam, North Holland, 1980.

K. V. Sujatha and S. Meenakshi Sundaram, “A Combined PCA-MLP model for Predicting Stock Index”, Proceedings of the 1st Amrita ACM-W Celebration on Women in Computing in India, Article No. 17, ACM, New York, NY, U.S.A., 2010.

K. V. Sujatha and S. Meenakshi Sundaram, “Regression, Theils and MLP Forecasting Models of Stock Index”, International Journal of Computer Engineering and Technology, Vol. 1, Issue 2, 2010, pp. 90-101.

K. V. Sujatha and S. Meenakshi Sundaram, “ A MLP, RBF Neural Network Model for Prediction in BSE SENSEX Data Set”, Proceedings of National Conference on Applied Mathematics, 2010.

K. V. Sujatha and S. Meenakshi Sundaram, “Stock Index Prediction Using Regression and Neural Network Models under Non Normal Conditions”, Proceeding of International Conference in Recent trends in Robotics and Communication Technologies”, 2010, pp. 58-62.

Lean Yu, Shouyang Wang and Kin Keung Lai,“Mining Stock Market Tendency Using GA Based Support Vector Machines”, X. Dengan Y. Ye (eds): wine 2005, LNCS, 3828, Springer Verlag Heidelberg 2005, pp 336-345.

M. Steiner and H. Wittemper, “Portfolio optimization with a neural Network implementation of the coherent market hypothesis”, European Jouranl of Operations Research, Volume 100, 1997, pp.27-40.

Mark O.Afolabi and Olatoyosi Olider, “Predicting Stock Prices Using a Hybrid Kohonen Self Organization Map”, Proceeding of the 40th Hawaii International Conference on System Science, 2007.

Myungsook Klassen,“Investigation of some Technical Indexes of Stock Forecasting in Neural Network”, World Academy of Science, Engineering and Technology, 5, 2005, pp. 75-79.

Pei Chan Chang and Chin Yuan Fan, “A Hybrid System Integrating a wavelet and TSK Fuzzy rules for stock Price Forecasting”, IEEE Transactions on systems, Man and cybernetics,Part C, Applications and reviews, Vol. 38, No. 6, 2008, pp. 802-815.

Ralph B. D’Agostino, “An omnibus test of normality for moderate and large samples”, Biometrika, Volume 58, 1971, pp. 341-348.

Samreen Fatima, and Ghulam Hussian, “Statistical models of KSE 100 index using Hybrid Financial Systems”, Neuro computing. Elsevier Science Publishers B. V. Volume 71, Issue 13-17, 2008, pp 2742-2746.

T. B. Trafalis, H. Ince and T. Mishina, “ Support Vector Regression in option pricing”, Proceedings of Conference on Computational Intelligence and Financial Engineering , Hong Kong, 2003

W. Leigh, M. Paz and R. Purvis, “An analysis of a hybrid neural network and pattern recognition techniques for predicting shork-term increases in the nyse”, Internation journal of Management Sciences, Volume 30, 2002, pp.69-76.

Xiaoping Yang, “Prediction of Stock Prices Based on PCA and BP Neural Networks”, Chinese Business Review, vol. 4, No. 5, S. No. 23, 2005, pp 64-68.

Zhang Yudong and Wu Lenan, “ Stock market prediction of S&P 500 via combination of improved BCO approach and BP neural network”, Pergamon Press, Inc. Expert Systems with ApplicationsVolume 36, Issue 5, 2009, pp 8849-8854.


Refbacks

  • There are currently no refbacks.