Enregistré dans:
Détails bibliographiques
Auteurs principaux: Wong, Steven Y. K., Chan, Jennifer S. K., Azizi, Lamiae
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2402.14476
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912034471280640
author Wong, Steven Y. K.
Chan, Jennifer S. K.
Azizi, Lamiae
author_facet Wong, Steven Y. K.
Chan, Jennifer S. K.
Azizi, Lamiae
contents Time-series with volatility clustering pose a unique challenge to uncertainty quantification (UQ) for returns forecasts. Methods for UQ such as Deep Evidential regression offer a simple way of quantifying return forecast uncertainty without the costs of a full Bayesian treatment. However, the Normal-Inverse-Gamma (NIG) prior adopted by Deep Evidential regression is prone to miscalibration as the NIG prior is assigned to latent mean and variance parameters in a hierarchical structure. Moreover, it also overparameterizes the marginal data distribution. These limitations may affect the accurate delineation of epistemic (model) and aleatoric (data) uncertainties. We propose a Scale Mixture Distribution as a simpler alternative which can provide favorable complexity-accuracy trade-off and assign separate subnetworks to each model parameter. To illustrate the performance of our proposed method, we apply it to two sets of financial time-series exhibiting volatility clustering: cryptocurrencies and U.S. equities and test the performance in some ablation studies.
format Preprint
id arxiv_https___arxiv_org_abs_2402_14476
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Quantifying neural network uncertainty under volatility clustering
Wong, Steven Y. K.
Chan, Jennifer S. K.
Azizi, Lamiae
Statistical Finance
Time-series with volatility clustering pose a unique challenge to uncertainty quantification (UQ) for returns forecasts. Methods for UQ such as Deep Evidential regression offer a simple way of quantifying return forecast uncertainty without the costs of a full Bayesian treatment. However, the Normal-Inverse-Gamma (NIG) prior adopted by Deep Evidential regression is prone to miscalibration as the NIG prior is assigned to latent mean and variance parameters in a hierarchical structure. Moreover, it also overparameterizes the marginal data distribution. These limitations may affect the accurate delineation of epistemic (model) and aleatoric (data) uncertainties. We propose a Scale Mixture Distribution as a simpler alternative which can provide favorable complexity-accuracy trade-off and assign separate subnetworks to each model parameter. To illustrate the performance of our proposed method, we apply it to two sets of financial time-series exhibiting volatility clustering: cryptocurrencies and U.S. equities and test the performance in some ablation studies.
title Quantifying neural network uncertainty under volatility clustering
topic Statistical Finance
url https://arxiv.org/abs/2402.14476