Author
Listed:
- Yoshua Bengio
- Réjean Ducharme
- Vincent-Philippe Lauzon
Abstract
Input/Output Hidden Markov Models (IOHMMs) are conditional hidden Markov models in which the emission (and possibly the transition) probabilities can be conditioned on an input sequence. For example, these conditional distributions can be linear, logistic, or non-linear (using for example multi-layer neural networks). We compare the generalization performance of several models which are special cases of Input/Output Hidden Markov Models on financial time-series prediction tasks: an unconditional Gaussian, a conditional linear Gaussian, a mixture of Gaussians, a mixture of conditional linear Gaussians, a hidden Markov model, and various IOHMMs. The experiments compare these models on predicting the conditional density of returns of market and sector indices. Note that the unconditional Gaussian estimates the first moment with the historical average. The results show that, although for the first moment the historical average gives the best results, for the higher moments, the IOHMMs yielded significantly better performance, as estimated by the out-of-sample likelihood. Input/Output Hidden Markov Models (IOHMMs) sont des modèles de Markov cachés pour lesquels les probabilités d'émission (et possiblement de transition) peuvent dépendre d'une séquence d'entrée. Par exemple, ces distributions conditionnelles peuvent être linéaires, logistique, ou non-linéaire (utilisant, par exemple, une réseau de neurones multi-couches). Nous comparons les performances de généralisation de plusieurs modèles qui sont des cas particuliers de IOHMMs pour des problèmes de prédictions de séries financières : une gaussienne inconditionnelle, une gaussienne linéaire conditionnelle, une mixture de gaussienne, une mixture de gaussiennes linéaires conditionnelles, un modèle de Markov caché, et divers IOHMMs. Les expériences comparent ces modèles sur leur prédictions de la densité conditionnelle des rendements des indices sectoriels et du marché. Notons qu'une gaussienne inconditionnelle estime le premier moment avec une moyenne historique. Les résultats montrent que, même si la moyenne historique donne les meilleurs résultats pour le premier moment, pour les moments d'ordres supérieurs les IOHMMs performent significativement mieux, comme estimé par la vraisemblance hors-échantillon.
Suggested Citation
Yoshua Bengio & Réjean Ducharme & Vincent-Philippe Lauzon, 2002.
"Experiments on the Application of IOHMMs to Model Financial Returns Series,"
CIRANO Working Papers
2002s-48, CIRANO.
Handle:
RePEc:cir:cirwor:2002s-48
Download full text from publisher
Corrections
All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:cir:cirwor:2002s-48. See general information about how to correct material in RePEc.
If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.
We have no bibliographic references for this item. You can help adding them by using this form .
If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Webmaster (email available below). General contact details of provider: https://edirc.repec.org/data/ciranca.html .
Please note that corrections may take a couple of weeks to filter through
the various RePEc services.