Using a dynamic artificial neural network for forecasting the volatility of a financial time series / Juan D. Velásquez,Sarah Gutiérrez,Carlos J. Franco

By: Material type: ArticleArticlePublication details: Medellin: Universidad de Medellin, 2013.Description: pp. 127-136 27 cmISSN:
  • 1692-3324
Uniform titles:
  • Ingenierías
Subject(s): Additional physical formats: IngenieríasOnline resources: In: Ingenierías In: López Pérez,Fredy IngenieriasSummary: 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.
Tags from this library: No tags from this library for this title. Log in to add tags.
Star ratings
    Average rating: 0.0 (0 votes)
No physical items for this record

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.

La capacidad de obtener pronósticos precisos de volatilidad es un tema importante para el analista financiero. En este artículo, utilizamos el modelo DAN2, un modelo de percepción multicapa y un modelo ARCH para predecir la varianza condicional mensual de los precios de las acciones. Los resultados muestran que el modelo DAN2 es más preciso para predecir la varianza dentro y fuera de la muestra que el otro consideró modelos para el conjunto de datos utilizado. Por lo tanto, se demuestra el valor de esta red neuronal como herramienta predictiva.

There are no comments on this title.

to post a comment.