Saved in:
Bibliographic Details
Main Authors: Hortúa, Héctor J., Mora-Valencia, Andrés
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2401.17042
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910499248013312
author Hortúa, Héctor J.
Mora-Valencia, Andrés
author_facet Hortúa, Héctor J.
Mora-Valencia, Andrés
contents Recently, deep learning techniques are gradually replacing traditional statistical and machine learning models as the first choice for price forecasting tasks. In this paper, we leverage probabilistic deep learning for inferring the volatility index VIX. We employ the probabilistic counterpart of WaveNet, Temporal Convolutional Network (TCN), and Transformers. We show that TCN outperforms all models with an RMSE around 0.189. In addition, it has been well known that modern neural networks provide inaccurate uncertainty estimates. For solving this problem, we use the standard deviation scaling to calibrate the networks. Furthermore, we found out that MNF with Gaussian prior outperforms Reparameterization Trick and Flipout models in terms of precision and uncertainty predictions. Finally, we claim that MNF with Cauchy and LogUniform prior distributions yield well calibrated TCN and WaveNet networks being the former that best infer the VIX values.
format Preprint
id arxiv_https___arxiv_org_abs_2401_17042
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Forecasting VIX using Bayesian Deep Learning
Hortúa, Héctor J.
Mora-Valencia, Andrés
Machine Learning
Recently, deep learning techniques are gradually replacing traditional statistical and machine learning models as the first choice for price forecasting tasks. In this paper, we leverage probabilistic deep learning for inferring the volatility index VIX. We employ the probabilistic counterpart of WaveNet, Temporal Convolutional Network (TCN), and Transformers. We show that TCN outperforms all models with an RMSE around 0.189. In addition, it has been well known that modern neural networks provide inaccurate uncertainty estimates. For solving this problem, we use the standard deviation scaling to calibrate the networks. Furthermore, we found out that MNF with Gaussian prior outperforms Reparameterization Trick and Flipout models in terms of precision and uncertainty predictions. Finally, we claim that MNF with Cauchy and LogUniform prior distributions yield well calibrated TCN and WaveNet networks being the former that best infer the VIX values.
title Forecasting VIX using Bayesian Deep Learning
topic Machine Learning
url https://arxiv.org/abs/2401.17042