Recurrent Neural Networks with more flexible memory: better predictions than rough volatility - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2023

Recurrent Neural Networks with more flexible memory: better predictions than rough volatility

Résumé

We extend recurrent neural networks to include several flexible timescales for each dimension of their output, which mechanically improves their abilities to account for processes with long memory or with highly disparate time scales. We compare the ability of vanilla and extended long short term memory networks (LSTMs) to predict asset price volatility, known to have a long memory. Generally, the number of epochs needed to train extended LSTMs is divided by two, while the variation of validation and test losses among models with the same hyperparameters is much smaller. We also show that the model with the smallest validation loss systemically outperforms rough volatility predictions by about 20% when trained and tested on a dataset with multiple time series.
Fichier principal
Vignette du fichier
njnfznpdfqchzbffjjwhszcbyybymgvc.pdf (477.13 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04165354 , version 1 (18-07-2023)

Identifiants

  • HAL Id : hal-04165354 , version 1

Citer

Damien Challet, Vincent Ragel. Recurrent Neural Networks with more flexible memory: better predictions than rough volatility. 2023. ⟨hal-04165354⟩
36 Consultations
69 Téléchargements

Partager

Gmail Facebook X LinkedIn More