Titre du document / Document title

A hybrid ARIMA and support vector machines model in stock price forecasting

Auteur(s) / Author(s)

PAI Ping-Feng ⁽¹⁾ ; LIN Chih-Sheng ⁽¹⁾ ;

Affiliation(s) du ou des auteurs / Author(s) Affiliation(s)

⁽¹⁾ Department of Industrial Engineering and Technology Management, Da-Yeh University, 112 Shan Jiau Road, Da-Tsuen, Chung-Hwa 515, TAIWAN, PROVINCE DE CHINE

Résumé / Abstract

Traditionally, the autoregressive integrated moving average (ARIMA) model has been one of the most widely used linear models in time series forecasting. However, the ARIMA model cannot easily capture the nonlinear patterns. Support vector machines (SVMs), a novel neural network technique, have been successfully applied in solving nonlinear regression estimation problems. Therefore, this investigation proposes a hybrid methodology that exploits the unique strength of the ARIMA model and the SVMs model in forecasting stock prices problems. Real data sets of stock prices were used to examine the forecasting accuracy of the proposed model. The results of computational tests are very promising.

Revue / Journal Title

Omega    ISSN  0305-0483   CODEN OMEGA6 

Source / Source

2005, vol. 33, n^o6, pp. 497-505 [9 page(s) (article)] (32 ref.)

Langue / Language

Anglais

Editeur / Publisher

Elsevier, Kidlington, ROYAUME-UNI  (1973) (Revue)

Mots-clés anglais / English Keywords

Regression analysis

;

Nonlinear problems

;

Non linear regression

;

Problem solving

;

Neural network

;

Linear time

;

Linear model

;

ARMA model

;

Modeling

;

Vector support machine

;

Statistical analysis

;

Occupation time

;

Strength

;

Capture

;

Time series

;

Autoregressive integrated moving average model

;

Forecasting

;

Mots-clés français / French Keywords

Analyse régression

;

Problème non linéaire

;

Régression non linéaire

;

Résolution problème

;

Réseau neuronal

;

Temps linéaire

;

Modèle linéaire

;

Modèle ARMA

;

Modélisation

;

Machine exemple support

;

Analyse statistique

;

Temps occupation

;

Résistance mécanique

;

Capture

;

Série temporelle

;

Modèle ARIMA

;

Prévision

;

Mots-clés espagnols / Spanish Keywords

Análisis regresión

;

Regresión no lineal

;

Resolución problema

;

Red neuronal

;

Tiempo lineal

;

Modelo lineal

;

Modelo ARMA

;

Modelización

;

Máquina ejemplo soporte

;

Análisis estadístico

;

Tiempo ocupación

;

Resistencia mecánica

;

Captura

;

Serie temporal

;

Modelo ARIMA

;

Previsión

;

Mots-clés d'auteur / Author Keywords

Artificial neural networks

;

ARIMA

;

Support vector machines

;

Time series forecasting

;

Stock prices

;

Localisation / Location

INIST-CNRS, Cote INIST : 16060, 35400013822532.0050