ANN Model to Predict Stock Prices at Stock Exchange Markets

Stock exchanges are considered major players in financial sectors of many countries. Most Stockbrokers, who execute stock trade, use technical, fundamental or time series analysis in trying to predict stock prices, so as to advise clients. However, these strategies do not usually guarantee good returns because they guide on trends and not the most likely price. It is therefore necessary to explore improved methods of prediction. The research proposes the use of Artificial Neural Network that is feedforward multi-layer perceptron with error backpropagation and develops a model of configuration 5:21:21:1 with 80% training data in 130,000 cycles. The research develops a prototype and tests it on 2008-2012 data from stock markets e.g. Nairobi Securities Exchange and New York Stock Exchange, where prediction results show MAPE of between 0.71% and 2.77%. Validation done with Encog and Neuroph realized comparable results. The model is thus capable of prediction on typical stock markets.

[1]  Teresa B. Ludermir,et al.  Comparison of new activation functions in neural network for forecasting financial time series , 2011, Neural Computing and Applications.

[2]  Charles Wong,et al.  CARTMAP: a neural network method for automated feature selection in financial time series forecasting , 2012, Neural Computing and Applications.

[3]  Shangkun Deng,et al.  Combining Technical Analysis with Sentiment Analysis for Stock Price Prediction , 2011, 2011 IEEE Ninth International Conference on Dependable, Autonomic and Secure Computing.

[4]  M. R. Martinez-Blanco,et al.  A study using the robust design of artificial neural networks methodology in neutron spectrometry , 2013, 2016 IEEE International Conference on Industrial Technology (ICIT).

[5]  Mohammad Hossein Fazel Zarandi,et al.  A hybrid fuzzy intelligent agent‐based system for stock price prediction , 2012, Int. J. Intell. Syst..

[6]  Matthew Butler,et al.  Multi-objective optimization with an evolutionary artificial neural network for financial forecasting , 2009, GECCO.

[7]  A. Ghaffari,et al.  Performance comparison of neural network training algorithms in modeling of bimodal drug delivery. , 2006, International journal of pharmaceutics.

[8]  Chien-Jen Huang,et al.  Using multi-stage data mining technique to build forecast model for Taiwan stocks , 2011, Neural Computing and Applications.

[9]  George D. C. Cavalcanti,et al.  Financial time series prediction using exogenous series and combined neural networks , 2009, 2009 International Joint Conference on Neural Networks.

[10]  Reza Aghababaeyan,et al.  Forecasting the Tehran Stock Market by Artificial Neural Network , 2011 .

[11]  John Yearwood,et al.  Predicting Australian Stock Market Index Using Neural Networks Exploiting Dynamical Swings and Intermarket Influences , 2003, J. Res. Pract. Inf. Technol..

[12]  R. K. Agrawal,et al.  A combination of artificial neural network and random walk models for financial time series forecasting , 2013, Neural Computing and Applications.

[13]  You-Shyang Chen,et al.  Forecasting Revenue Growth Rate Using Fundamental Analysis: A Feature Selection Based Rough Sets Approach , 2007, Fourth International Conference on Fuzzy Systems and Knowledge Discovery (FSKD 2007).

[14]  Radu Iacomin,et al.  Stock market prediction , 2015, 2015 19th International Conference on System Theory, Control and Computing (ICSTCC).

[15]  Milan Chytrý,et al.  Supervised classification of plant communities with artificial neural networks , 2005 .

[16]  B Uma Devi,et al.  A Study on Stock Market Analysis for Stock Selection - Naïve Investors' Perspective using Data Mining Technique , 2011 .

[17]  Akter Hussain,et al.  Price Prediction of Share Market using Artificial Neural Network (ANN) , 2011 .

[18]  Jun Zhang,et al.  Chaotic Time Series Prediction Using a Neuro-Fuzzy System with Time-Delay Coordinates , 2008, IEEE Transactions on Knowledge and Data Engineering.