Estimating returns and condicional volatility: a comparison between the ARMA-GARCH-M Models and the Backpropagation Neural Network

Econometric models have usually estimated both returns and conditional volatility in financial assets. This paper is intended in the comparison of this traditional approach with the more recent Backpropagation neural network. When applied to the Spanish Ibex-35 stock market index, we find that the n...

Descripción completa

Detalles Bibliográficos
Autores: García García, Fernando|||0000-0001-6364-520X, Guijarro, Francisco|||0000-0002-8803-5165, Moya Clemente, Ismael|||0000-0002-1219-1890, Oliver-Muncharaz, Javier|||0000-0001-5317-6489
Tipo de recurso: artículo
Fecha de publicación:2012
País:España
Institución:Universitat Politècnica de València (UPV)
Repositorio:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Idioma:inglés
OAI Identifier:oai:riunet.upv.es:10251/60000
Acceso en línea:https://riunet.upv.es/handle/10251/60000
Access Level:acceso abierto
Palabra clave:Conditional volatility
Backpropagation neural network
GARCH-M
ECONOMIA FINANCIERA Y CONTABILIDAD
Descripción
Sumario:Econometric models have usually estimated both returns and conditional volatility in financial assets. This paper is intended in the comparison of this traditional approach with the more recent Backpropagation neural network. When applied to the Spanish Ibex-35 stock market index, we find that the neural network achieved significantly better performance in predicting conditional volatility, but similar results when predicting financial returns.