AUTHORS: Roumen Trifonov

Download as PDF

ABSTRACT: Artificial neural network is one of the intelligent methods in Artificial Intelligence. There are many decisions of different tasks using neural network approach. The forecasting problems are high challenge and researchers use different methods to solve them. The financial tasks related to forecasting, classification and management using artificial neural network are considered. The technology and methods for prediction of financial data as well as the developed system for forecasting of financial markets via neural network are described in the paper. The designed architecture of a neural network using four different technical indicators is presented. The developed neural network is used for forecasting movement of stock prices one day ahead and consists of an input layer, one hidden layer and an output layer. The training method is a training algorithm with back propagation of the error. The main advantage of the developed system is self-determination of the optimal topology of neural network, due to which it becomes flexible and more precise. The proposed system with neural network is universal and can be applied to various financial instruments using only basic technical indicators as input data.

KEYWORDS: neural networks, forecasting, training algorithm, financial indicators, backpropagation

REFERENCES:

[1] A. V. Devadoss , T. A. A. Ligori., 'Stock Prediction Using Artificial Neural Networks,' International Journal of Data Mining Techniques and Applications, Vol 02, December, pp. 283-291 , 2013.

[2] Jingtao Yao, Chew Lim Tan, 'Guidelines for Financial Forecasting with Neural Networks,' in Neural Information Processing, Shanghai, 2001.

[3] C. Hsieh, 'Some Potential Applications of Artificial Neural Systems in Financial Management,' Journal of Systems Management, Vol. 44 N 4, p12(4), April 1993.

[4] Fred Kitchens, Thomas Harris, 'Genetic Adaptive Neural Networks for Prediction,' International Journal of Engineering and Advanced Research Technology (IJEART), vol. 1 , no. 6, pp. 27-30, December 2015.

[5] Jerzy Balicki, Piotr Przybyłek, Marcin Zadroga, Marcin Zakidalski, 'Methods of Artificial Intelligence for Prediction and Prevention Crisis Situations in Banking,' Gdansk, Poland, 15-17 May 2014.

[6] Nazari M., Alidadi M., 'Measuring credit risk of bank customers using artificial neural network,' Journal of Management Research, vol. 5, No. 2, 2013.

[7] C. Gangolf, Models and Methods for Automated, University of Saarland, 2016.

[8] Fred Kitchens, Thomas Harris, 'Genetic Adaptive Neural Networks for Prediction,' International Journal of Engineering and Advanced Research Technology (IJEART), Vol. 1 , № 6, pp. 27-30, December 2015.

[9] O. Coupelon, ' Neural Network Modeling for Stock Movement Prediction a State of the Art,' 2007.

[Online]. Available: http://olivier.coupelon.free.fr/Neural_network_ modeling_for_stock_movemen_prediction.pdf.

[10] Finnie., Bruce J. Vanstone and Gavin, 'An empirical methodology for developing stockmarket trading systems using artificial neural networks,,' 2009.

[Online]. Available: http://epublications.bond.edu.au/infotech_pubs/ 21.

[11] A.H.i Moghaddama, M.H. Moghaddamb, M. Esfandyari, 'Stock market index prediction using artificial neural network,' Journal of Economics, Finance and Administrative Science, No. 21, p. 89–93, 2016.

[12] Martin T. Hagan, Howard B. Demuth, Mark Hudson Beale, Orlando De Jesús, Neural Network Design, 2 ed., eBook.