GARCH-Informed Neural Networks for Volatility Prediction in Financial Markets
(2024) 5th ACM International Conference on AI in Finance, ICAIF 2024 p.600-607- Abstract
Volatility, which indicates the dispersion of returns, is a crucial measure of risk and is hence used extensively for pricing and discriminating between different financial investments. As a result, accurate volatility prediction receives extensive attention. The Generalized Autoregressive Conditional Heteroscedasticity (GARCH) model and its succeeding variants are well established models for stock volatility forecasting. More recently, deep learning models have gained popularity in volatility prediction as they demonstrated promising accuracy in certain time series prediction tasks. Inspired by Physics-Informed Neural Networks (PINN), we constructed a new, hybrid Deep Learning model that combines the strengths of GARCH with the... (More)
Volatility, which indicates the dispersion of returns, is a crucial measure of risk and is hence used extensively for pricing and discriminating between different financial investments. As a result, accurate volatility prediction receives extensive attention. The Generalized Autoregressive Conditional Heteroscedasticity (GARCH) model and its succeeding variants are well established models for stock volatility forecasting. More recently, deep learning models have gained popularity in volatility prediction as they demonstrated promising accuracy in certain time series prediction tasks. Inspired by Physics-Informed Neural Networks (PINN), we constructed a new, hybrid Deep Learning model that combines the strengths of GARCH with the flexibility of a Long Short-Term Memory (LSTM) Deep Neural Network (DNN), thus capturing and forecasting market volatility more accurately than either class of models are capable of on their own. We refer to this novel model as a GARCH-Informed Neural Network (GINN). When compared to other time series models, GINN showed superior out-of-sample prediction performance in terms of the Coefficient of Determination (R2), Mean Squared Error (MSE), and Mean Absolute Error (MAE).
(Less)
- author
- Xu, Zeda ; Liechty, John ; Benthall, Sebastian ; Skar-Gislinge, Nicholas LU and McComb, Christopher
- organization
- publishing date
- 2024-11
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- hybrid model, neural networks, physics informed machine learning, volatility prediction
- host publication
- ICAIF 2024 - 5th ACM International Conference on AI in Finance
- pages
- 8 pages
- publisher
- Association for Computing Machinery (ACM)
- conference name
- 5th ACM International Conference on AI in Finance, ICAIF 2024
- conference location
- Brooklyn, United States
- conference dates
- 2024-11-14 - 2024-11-17
- external identifiers
-
- scopus:85214905097
- ISBN
- 9798400710810
- DOI
- 10.1145/3677052.3698600
- language
- English
- LU publication?
- yes
- id
- 1d7707f4-dbef-4084-b91d-cc1e59784322
- date added to LUP
- 2025-02-24 13:42:50
- date last changed
- 2025-04-04 14:45:05
@inproceedings{1d7707f4-dbef-4084-b91d-cc1e59784322,
abstract = {{<p>Volatility, which indicates the dispersion of returns, is a crucial measure of risk and is hence used extensively for pricing and discriminating between different financial investments. As a result, accurate volatility prediction receives extensive attention. The Generalized Autoregressive Conditional Heteroscedasticity (GARCH) model and its succeeding variants are well established models for stock volatility forecasting. More recently, deep learning models have gained popularity in volatility prediction as they demonstrated promising accuracy in certain time series prediction tasks. Inspired by Physics-Informed Neural Networks (PINN), we constructed a new, hybrid Deep Learning model that combines the strengths of GARCH with the flexibility of a Long Short-Term Memory (LSTM) Deep Neural Network (DNN), thus capturing and forecasting market volatility more accurately than either class of models are capable of on their own. We refer to this novel model as a GARCH-Informed Neural Network (GINN). When compared to other time series models, GINN showed superior out-of-sample prediction performance in terms of the Coefficient of Determination (R2), Mean Squared Error (MSE), and Mean Absolute Error (MAE).</p>}},
author = {{Xu, Zeda and Liechty, John and Benthall, Sebastian and Skar-Gislinge, Nicholas and McComb, Christopher}},
booktitle = {{ICAIF 2024 - 5th ACM International Conference on AI in Finance}},
isbn = {{9798400710810}},
keywords = {{hybrid model; neural networks; physics informed machine learning; volatility prediction}},
language = {{eng}},
pages = {{600--607}},
publisher = {{Association for Computing Machinery (ACM)}},
title = {{GARCH-Informed Neural Networks for Volatility Prediction in Financial Markets}},
url = {{http://dx.doi.org/10.1145/3677052.3698600}},
doi = {{10.1145/3677052.3698600}},
year = {{2024}},
}