Value-at-risk forecasting- based on textual information and a hybrid deep learning-based approach

Yangfan Cao, Wei Chong Choo and Bolaji Tunde Matemilola

International Review of Economics & Finance, 2025, vol. 103, issue C

Abstract: The recent rise in deep learning and natural language processing (NLP) applications has notably improved productivity across different fields. This research aims to refine Value-at-Risk (VaR) model accuracy by leveraging text mining and deep learning. It first uses NLP to analyze online news sentiments, integrating these as variables to boost stock market risk forecasts and assess their effect on VaR accuracy. Additionally, the study combines predictions from four unique Generalized AutoRegressive Conditional Heteroskedasticity (GARCH)-type models into advanced Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN)-LSTM models to see if this boosts VaR precision. It also explores how textual data impacts VaR predictions over short and longer periods, using 7 and 20-day rolling windows. The analysis, using S&P500 (SPY), Dow Jones Industrial Average (DJI), and Nasdaq Composite (IXIC) data from 2012 to 2023 alongside news headlines, tests these approaches. The results confirm that incorporating textual information into the VaR model enhances its forecasting accuracy, highlighting the benefits of applying deep learning techniques in this process.

Keywords: VaR; GARCH; LSTM; CNN; NLP; Sentiment analysis (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S1059056025005660
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:reveco:v:103:y:2025:i:c:s1059056025005660

DOI: 10.1016/j.iref.2025.104403

Access Statistics for this article

International Review of Economics & Finance is currently edited by H. Beladi and C. Chen

More articles in International Review of Economics & Finance from Elsevier
Bibliographic data for series maintained by Catherine Liu ().