Moving intervals for nonlinear time series forecasting

N. Agell, Francisco Javier Ruiz Vegas, Albert Samà Monsonís, German Sánchez Hernández

Producció científica: Contribució a una conferènciaContribució

Resum

In this paper a new forecasting methodology to be used on time series prediction is introduced. The considered nonlinear method is based on support vector machines (SVM) using an interval kernel. An extended intersection kernel is introduced to discriminate between disjoint intervals in reference to the existing distance among them. The model presented is applied to forecast exchange ratios using six world's major currencies. The results obtained show that SVMs based on interval kernel have a similar behavior than other SVM classical forecasting approaches, allowing its performance to be seen as very promising when using high frequency data.
Idioma originalAnglès
Estat de la publicacióPublicada - 20 d’oct. 2010
Esdeveniment13th International Conference of the Catalan Association for Artificial Intelligence -
Durada: 20 d’oct. 201022 d’oct. 2010

Conferència

Conferència13th International Conference of the Catalan Association for Artificial Intelligence
Període20/10/1022/10/10

Fingerprint

Navegar pels temes de recerca de 'Moving intervals for nonlinear time series forecasting'. Junts formen un fingerprint únic.

Com citar-ho