Hybrid fuzzy neural network versus backpropagation neural network: An application to predict the Ibex-35 index stock

J Oliver Muncharaz

doi:10.46503/alep9985

Abstract

The use of neural networks has been extended in all areas of knowledge due to the good results being obtained in the resolution of the different problems posed. The prediction of prices in general, and stock market prices in particular, represents one of the main objectives of the use of neural networks in finance. This paper presents the analysis of the efficiency of the hybrid fuzzy neural network against a backpropagation type neural network in the price prediction of the Spanish stock exchange index (IBEX-35). The paper is divided into two parts. In the first part, the main characteristics of neural networks such as hybrid fuzzy and backpropagation, their structures and learning rules are presented. In the second part, the prediction of the IBEX-35 stock exchange index with these networks is analyzed, measuring the efficiency of both as a function of the prediction errors committed. For this purpose, both networks have been constructed with the same inputs and for the same sample period. The results obtained suggest that the Hybrid fuzzy neuronal network is much more efficient than the widespread backpropagation neuronal network for the sample analysed.

Highlights

Cómo citar este artículo: Oliver Muncharaz, J. ( ) Red neuronal fuzzy híbrida versus red neuronal backpropagation: Aplicación a la predicción del índice bursátil Ibex
E iciency of both as a function of the prediction errors committed. Both networks have been constructed with the same inputs and for the same sample period
The results obtained suggest that the Hybrid fuzzy neural network is much more e icient than the widespread backpropagation neuronal network for the sample analysed

Summary

Javier Oliver Muncharaz ID

El uso de las redes neuronales se ha extendido en todas las áreas de conocimiento por los buenos resultados que se están obteniendo en la resolución de los diferentes problemas planteados. La predicción sobre los precios en general, y los precios bursátiles en particular, representa uno de los principales objetivos del uso de las redes neuronales en finanzas. En este trabajo se presenta el análisis de la eficiencia de la hybrid fuzzy neural network frente a una red neuronal de tipo backpropagation en la predicción del precio del índice bursátil Español (IBEX- ). En la primera se expone las principales características de las redes neuronales como la hybrid fuzzy y la Backpropagation, sus estructuras y sus reglas de aprendizaje. En la segunda parte se analiza la predicción del índice bursátil IBEX- con estas redes midiendo la eficiencia de ambas en función de los errores de predicción cometidos. Los resultados obtenidos sugieren que la Hybrid fuzzy neuronal network es mucho más eficiente que la, tan extendida, red neuronal backpropagation para la muestra analizada

Modelos de redes neuronales

Javier Oliver Muncharaz

RMSE MAE