A COMPARISON OF NEURAL NETWORKS AND ARCHGARCH MODELS TO PREDICT CHANGES IN SHARE PRICES. AN APPLICATION TO THE CASE OF STOCKS IN THE TELECOMUNICATIONS INDUSTRY

In recent years, there have been attempts to test the theory of market efficiency, using more efficient and accurate models to predict changes in the prices of various financial instruments. Actually there are two ways to predict such variations: parametric and nonparametric models. In the first gro...

Descripción completa

Detalles Bibliográficos
Autores principales: DIP, Juan Antonio, ROMERO, Patricia Isabel
Formato: Artículo publishedVersion
Lenguaje:Español
Publicado: Centro de Investigación en Métodos Cuantitativos Aplicados a la Economía y la Gestión (CMA) 2015
Acceso en línea:https://ojs.economicas.uba.ar/RIMF/article/view/1505
https://repositoriouba.sisbi.uba.ar/gsdl/cgi-bin/library.cgi?a=d&c=modelfin&d=1505_oai
Aporte de:
Repositorio Digital de la Universidad de Buenos Aires (UBA) de Universidad de Buenos Aires
id I28-R145-1505_oai
record_format dspace
spelling I28-R145-1505_oai2025-02-11 DIP, Juan Antonio ROMERO, Patricia Isabel 2015-12-10 In recent years, there have been attempts to test the theory of market efficiency, using more efficient and accurate models to predict changes in the prices of various financial instruments. Actually there are two ways to predict such variations: parametric and nonparametric models. In the first group there are various statistical-econometric models, while in the second there are artificial intelligence techniques as neural networks and genetic algorithms. The use of neural networks for predicting the behaviour of economic variables has increased greatly in recent years. This paper describes the design of solutions to forecast the share price of Telecom Argentina SA, which is listed on the Stock Exchange of Buenos Aires, in the period 2005-2012 from the use of a technique called Principal Component Analysis. The results are presented based on traditional models Arch-Garch and backpropagation networks. Additionally, a comparison between the methodologies is presented, considering the degree of prediction achieved. Durante los últimos años se ha intentado contrastar la teoría de eficiencia de mercado, a partir de modelos más eficientes y exactos para predecir variaciones en los precios de los distintos instrumentos financieros. Actualmente existen dos vías para predecir dichas variaciones: modelos paramétricos y modelos no paramétricos. Dentro del primer grupo se encuentran diversos modelos estadístico-econométricos, mientras que dentro del segundo se encuentran técnicas de inteligencia artificial, como las redes neuronales y los algoritmos genéticos. La utilización de redes neuronales para la predicción del comportamiento de variables económicas ha aumentado en gran medida durante los últimos años. Este trabajo describe el diseño de soluciones para pronosticar el precio de la acción de la sociedad Telecom Argentina S.A., la cual cotiza en la Bolsa de Comercio de Buenos Aires, en el período 2005-2012 a partir del uso de la técnica de análisis de componentes principales. Se presentan resultados basados en modelos tradicionales Arch-Garch y en un sistema de redes backpropagation. Adicionalmente, se presenta una comparación entre las metodologías, teniendo en cuenta el grado de predicción logrado. application/pdf https://ojs.economicas.uba.ar/RIMF/article/view/1505 spa Centro de Investigación en Métodos Cuantitativos Aplicados a la Economía y la Gestión (CMA) https://ojs.economicas.uba.ar/RIMF/article/view/1505/2131 Revista de Investigación en Modelos Financieros; Vol. 2 (2015): Revista de Investigación en Modelos Financieros; 1-29 2250-6861 2250-687X A COMPARISON OF NEURAL NETWORKS AND ARCHGARCH MODELS TO PREDICT CHANGES IN SHARE PRICES. AN APPLICATION TO THE CASE OF STOCKS IN THE TELECOMUNICATIONS INDUSTRY UNA COMPARACIÓN DE REDES NEURONALES Y MODELOS ARCH-GARCH PARA PREDECIR VARIACIONES EN EL PRECIO DE ACCIONES. APLICACIÓN A UN CASO DE ACCIONES DE TELEFONÁA. info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion https://repositoriouba.sisbi.uba.ar/gsdl/cgi-bin/library.cgi?a=d&c=modelfin&d=1505_oai
institution Universidad de Buenos Aires
institution_str I-28
repository_str R-145
collection Repositorio Digital de la Universidad de Buenos Aires (UBA)
language Español
orig_language_str_mv spa
description In recent years, there have been attempts to test the theory of market efficiency, using more efficient and accurate models to predict changes in the prices of various financial instruments. Actually there are two ways to predict such variations: parametric and nonparametric models. In the first group there are various statistical-econometric models, while in the second there are artificial intelligence techniques as neural networks and genetic algorithms. The use of neural networks for predicting the behaviour of economic variables has increased greatly in recent years. This paper describes the design of solutions to forecast the share price of Telecom Argentina SA, which is listed on the Stock Exchange of Buenos Aires, in the period 2005-2012 from the use of a technique called Principal Component Analysis. The results are presented based on traditional models Arch-Garch and backpropagation networks. Additionally, a comparison between the methodologies is presented, considering the degree of prediction achieved.
format Artículo
publishedVersion
author DIP, Juan Antonio
ROMERO, Patricia Isabel
spellingShingle DIP, Juan Antonio
ROMERO, Patricia Isabel
A COMPARISON OF NEURAL NETWORKS AND ARCHGARCH MODELS TO PREDICT CHANGES IN SHARE PRICES. AN APPLICATION TO THE CASE OF STOCKS IN THE TELECOMUNICATIONS INDUSTRY
author_facet DIP, Juan Antonio
ROMERO, Patricia Isabel
author_sort DIP, Juan Antonio
title A COMPARISON OF NEURAL NETWORKS AND ARCHGARCH MODELS TO PREDICT CHANGES IN SHARE PRICES. AN APPLICATION TO THE CASE OF STOCKS IN THE TELECOMUNICATIONS INDUSTRY
title_short A COMPARISON OF NEURAL NETWORKS AND ARCHGARCH MODELS TO PREDICT CHANGES IN SHARE PRICES. AN APPLICATION TO THE CASE OF STOCKS IN THE TELECOMUNICATIONS INDUSTRY
title_full A COMPARISON OF NEURAL NETWORKS AND ARCHGARCH MODELS TO PREDICT CHANGES IN SHARE PRICES. AN APPLICATION TO THE CASE OF STOCKS IN THE TELECOMUNICATIONS INDUSTRY
title_fullStr A COMPARISON OF NEURAL NETWORKS AND ARCHGARCH MODELS TO PREDICT CHANGES IN SHARE PRICES. AN APPLICATION TO THE CASE OF STOCKS IN THE TELECOMUNICATIONS INDUSTRY
title_full_unstemmed A COMPARISON OF NEURAL NETWORKS AND ARCHGARCH MODELS TO PREDICT CHANGES IN SHARE PRICES. AN APPLICATION TO THE CASE OF STOCKS IN THE TELECOMUNICATIONS INDUSTRY
title_sort comparison of neural networks and archgarch models to predict changes in share prices. an application to the case of stocks in the telecomunications industry
publisher Centro de Investigación en Métodos Cuantitativos Aplicados a la Economía y la Gestión (CMA)
publishDate 2015
url https://ojs.economicas.uba.ar/RIMF/article/view/1505
https://repositoriouba.sisbi.uba.ar/gsdl/cgi-bin/library.cgi?a=d&c=modelfin&d=1505_oai
work_keys_str_mv AT dipjuanantonio acomparisonofneuralnetworksandarchgarchmodelstopredictchangesinsharepricesanapplicationtothecaseofstocksinthetelecomunicationsindustry
AT romeropatriciaisabel acomparisonofneuralnetworksandarchgarchmodelstopredictchangesinsharepricesanapplicationtothecaseofstocksinthetelecomunicationsindustry
AT dipjuanantonio unacomparacionderedesneuronalesymodelosarchgarchparapredecirvariacionesenelpreciodeaccionesaplicacionauncasodeaccionesdetelefonaa
AT romeropatriciaisabel unacomparacionderedesneuronalesymodelosarchgarchparapredecirvariacionesenelpreciodeaccionesaplicacionauncasodeaccionesdetelefonaa
AT dipjuanantonio comparisonofneuralnetworksandarchgarchmodelstopredictchangesinsharepricesanapplicationtothecaseofstocksinthetelecomunicationsindustry
AT romeropatriciaisabel comparisonofneuralnetworksandarchgarchmodelstopredictchangesinsharepricesanapplicationtothecaseofstocksinthetelecomunicationsindustry
_version_ 1825551179453562880

Ejemplares similares