APPLICABILITY OF NEURAL NETWORKS IN FINANCE ACROSS DIFFERENT COUNTRIES

Gerardo Alfonso Perez

Abstract


Countries across the globe have cultural and socioeconomic differences that can translate into significantly different behaviors of their respective stock market. In this article it is analyzed if neural networks applied to four different countries such as France, China, Germany and Japan, produce similar results. Neural networks are a powerful machine learning approach that has been applied in several stock markets for forecasting purposes. The simplicity of application and relative accurate forecast are likely some of the reasons behind the expansion of usage of these techniques in finance. It will be shown in this article that while there are significant differences between these four market neural networks seem to produce comparable but not identical results in all the four markets analyzed.

 


Full Text:

PDF

References


. Forecasting stock market indices with recurrent neural networks. Applications of computer aided time series modelling. 291-335. 1997.

. Gately Edward. Neural networks for financial forecasting. John Wiley & Sons. 1996.

. Gencay Ramazan. Stengos Thanasis. Moving average rules, volume and the predictability of security returns with feedforward networks Journal of forecasting. 17. 1998.

. Gunther Franke, Fritsch Stefan. Neuralnet: Training of neural networks. The research journal. Volume 2. 2010.

. Kovack Benedek, Toth Janos. Estimating reaction rate constants with neural networks. International journal of applied mathematics and computer sciences. Vol 4. 2007.

. Maser Samy. Predicting learners performance using artificial neural networks in linear programming intelligent tutoring systems. International journal of artificial intelligence & aplpications. Volume 3. 2012.

. Mohamad H, Ibrahim A, Massoud H. Modelling the financial performance of construction companies using neural network via genetic algorithm. Canadian journal of civil engineering. 2014.

. Nitish Srivastava, Hinton Geoffrey, Krizhevsky Alex, Sutskever Ilya, Salakutdinov Ruslan. Dropout: a simple way to prevent neural networks from over-fitting. Journal of machine learning research 15. 1929-1958. 2014.

. Patel B. Yalamalle Sunil. Stock price prediction using artificial neural network. International journal of innovative research in science. 2014.

. Romero-Mendez Ricardo, Hidalgo Lopez Juan Manuel. Use of artificial neural networks for prediction of convective heat transfer in evaporative units. Ingenieria investigacion y tecnologia. Volume XV. 2014.

. Stanly Kenneth, Miikkulainen Risto. Evolving neural networks through augmenting topologies. The MIT press journals. 2000.


Refbacks

  • There are currently no refbacks.