Using a dynamic artificial neural network for forecasting the volatility of a financial time series.

The ability to obtain accurate volatility forecasts is an important issue for the financial analyst. In this paper, we use the DAN2 model, a multilayer perceptronand an ARCH model to predict the monthly conditional variance of stock prices.The results show that DAN2 model is more accurate for predic...

ver descrição completa

Detalhes bibliográficos
Autores: Velásquez, Juan D., Gutiérrez, Sarah, Franco, Carlos J.
Tipo de documento: artigo
Estado:Versão publicada
Data de publicação:2013
País:Colombia
Recursos:Universidad de Medellín
Repositório:Repositorio UDEM
Idioma:espanhol
OAI Identifier:oai:repository.udem.edu.co:11407/962
Acesso em linha:http://hdl.handle.net/11407/962
Access Level:Acceso aberto
Palavra-chave:Volatility forecast
prediction
nonlinear models
heteroskedasticity
volatilidad (finanzas)
modelos no lineales
heterocedasticidad
Descrição
Resumo:The ability to obtain accurate volatility forecasts is an important issue for the financial analyst. In this paper, we use the DAN2 model, a multilayer perceptronand an ARCH model to predict the monthly conditional variance of stock prices.The results show that DAN2 model is more accurate for predicting in-sample andout-of-sample variance that the other considered models for the used data set. Thus, the value of this neural network as a predictive tool is demonstrated.