High frequency volatility forecasting and risk assessment using neural networks-based heteroscedasticity model

High frequency volatility forecasting is essential for timely risk management and informed decision-making in dynamic financial markets. However, accurate forecasting is challenging due to the rapid nature of market movements and the complexity of underlying economic factors. This paper introduces a...

Full description

Saved in:
Bibliographic Details
Main Author: Aryan, Bhambu (author)
Other Authors: Bera, Koushik (author), Natarajan, Selvaraju (author), Suganthan, Ponnuthurai Nagaratnam (author)
Format: article
Published: 2025
Subjects:
Online Access:http://dx.doi.org/10.1016/j.engappai.2025.110397
https://www.sciencedirect.com/science/article/pii/S0952197625003975
http://hdl.handle.net/10576/64848
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1857415087575269376
author Aryan, Bhambu
author2 Bera, Koushik
Natarajan, Selvaraju
Suganthan, Ponnuthurai Nagaratnam
author2_role author
author
author
author_facet Aryan, Bhambu
Bera, Koushik
Natarajan, Selvaraju
Suganthan, Ponnuthurai Nagaratnam
author_role author
dc.creator.none.fl_str_mv Aryan, Bhambu
Bera, Koushik
Natarajan, Selvaraju
Suganthan, Ponnuthurai Nagaratnam
dc.date.none.fl_str_mv 2025-05-11T11:54:06Z
2025-03-11
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv http://dx.doi.org/10.1016/j.engappai.2025.110397
Nagaratnam, S. (2025). High frequency volatility forecasting and risk assessment using neural networks-based heteroscedasticity model.
0952-1976
https://www.sciencedirect.com/science/article/pii/S0952197625003975
http://hdl.handle.net/10576/64848
149
dc.language.none.fl_str_mv en
dc.publisher.none.fl_str_mv Elsevier
dc.rights.none.fl_str_mv http://creativecommons.org/licenses/by/4.0/
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Volatility forecasting
Risk assessment
Generalized autoregressive conditional heteroscedasticity models
High frequency data
Neural network
Deep learning
Finance
dc.title.none.fl_str_mv High frequency volatility forecasting and risk assessment using neural networks-based heteroscedasticity model
dc.type.none.fl_str_mv Article
info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/article
description High frequency volatility forecasting is essential for timely risk management and informed decision-making in dynamic financial markets. However, accurate forecasting is challenging due to the rapid nature of market movements and the complexity of underlying economic factors. This paper introduces a novel architecture combining Generalized Autoregressive Conditional Heteroscedasticity (GARCH) and Multi-layer Perceptron (MLP)-based models for enhanced volatility forecasting and risk assessment, where input variables are processed through GARCH-type models for volatility forecasting. The proposed GARCH-based MLP-Mixer (GaMM) model incorporates the stacking of multi-layer perceptrons, enabling deep representation learning, facilitating the extraction of temporal and feature information through operations along both time and feature dimensions, and addressing the complexity of high-frequency time-series data. The proposed model is evaluated on three high frequency financial times series datasets over three different years. The computational results demonstrate the proposed model’s superior performance over sixteen forecasting methods in three error metrics, Value-at-risk, and statistical tests for high frequency volatility forecasting and risk assessment tasks.
eu_rights_str_mv openAccess
format article
id qu_1a72b5afd6aea53ca343ff4267ad3bac
identifier_str_mv Nagaratnam, S. (2025). High frequency volatility forecasting and risk assessment using neural networks-based heteroscedasticity model.
0952-1976
149
language_invalid_str_mv en
network_acronym_str qu
network_name_str Qatar University repository
oai_identifier_str oai:qspace.qu.edu.qa:10576/64848
publishDate 2025
publisher.none.fl_str_mv Elsevier
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv http://creativecommons.org/licenses/by/4.0/
spelling High frequency volatility forecasting and risk assessment using neural networks-based heteroscedasticity modelAryan, BhambuBera, KoushikNatarajan, SelvarajuSuganthan, Ponnuthurai NagaratnamVolatility forecastingRisk assessmentGeneralized autoregressive conditional heteroscedasticity modelsHigh frequency dataNeural networkDeep learningFinanceHigh frequency volatility forecasting is essential for timely risk management and informed decision-making in dynamic financial markets. However, accurate forecasting is challenging due to the rapid nature of market movements and the complexity of underlying economic factors. This paper introduces a novel architecture combining Generalized Autoregressive Conditional Heteroscedasticity (GARCH) and Multi-layer Perceptron (MLP)-based models for enhanced volatility forecasting and risk assessment, where input variables are processed through GARCH-type models for volatility forecasting. The proposed GARCH-based MLP-Mixer (GaMM) model incorporates the stacking of multi-layer perceptrons, enabling deep representation learning, facilitating the extraction of temporal and feature information through operations along both time and feature dimensions, and addressing the complexity of high-frequency time-series data. The proposed model is evaluated on three high frequency financial times series datasets over three different years. The computational results demonstrate the proposed model’s superior performance over sixteen forecasting methods in three error metrics, Value-at-risk, and statistical tests for high frequency volatility forecasting and risk assessment tasks.Open Access funding provided by the Qatar National Library. The authors also acknowledge the financial support provided by the Science and Engineering Research Board (SERB), Government of India (Grant No. MTR/2021/000425) and the supercomputing resources from the IIT Guwahati for conducting the research work presented in this paper.Elsevier2025-05-11T11:54:06Z2025-03-11Articleinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://dx.doi.org/10.1016/j.engappai.2025.110397Nagaratnam, S. (2025). High frequency volatility forecasting and risk assessment using neural networks-based heteroscedasticity model.0952-1976https://www.sciencedirect.com/science/article/pii/S0952197625003975http://hdl.handle.net/10576/64848149enhttp://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:qspace.qu.edu.qa:10576/648482025-05-11T19:07:42Z
spellingShingle High frequency volatility forecasting and risk assessment using neural networks-based heteroscedasticity model
Aryan, Bhambu
Volatility forecasting
Risk assessment
Generalized autoregressive conditional heteroscedasticity models
High frequency data
Neural network
Deep learning
Finance
status_str publishedVersion
title High frequency volatility forecasting and risk assessment using neural networks-based heteroscedasticity model
title_full High frequency volatility forecasting and risk assessment using neural networks-based heteroscedasticity model
title_fullStr High frequency volatility forecasting and risk assessment using neural networks-based heteroscedasticity model
title_full_unstemmed High frequency volatility forecasting and risk assessment using neural networks-based heteroscedasticity model
title_short High frequency volatility forecasting and risk assessment using neural networks-based heteroscedasticity model
title_sort High frequency volatility forecasting and risk assessment using neural networks-based heteroscedasticity model
topic Volatility forecasting
Risk assessment
Generalized autoregressive conditional heteroscedasticity models
High frequency data
Neural network
Deep learning
Finance
url http://dx.doi.org/10.1016/j.engappai.2025.110397
https://www.sciencedirect.com/science/article/pii/S0952197625003975
http://hdl.handle.net/10576/64848