NEWS IV: A model with news and implied volatility for enhanced volatility prediction

Vitor Gentini () and Marcio Issao Nakane ()

No 2026_25, Working Papers, Department of Economics from University of São Paulo (FEA-USP)

Abstract: This paper examines whether implied volatility and textual news jointly improve volatility forecasting. We propose the NEWS IV model, which combines the realized-variance components of the HAR model with option-implied variance and news topics extracted via Latent Dirichlet Allocation within a flexible machine learning framework. Using data for the Ibovespa ETF and major Brazilian stocks, we evaluate predictive performance relative to HAR-type benchmarks across multiple horizons. We show that the model augmented with implied volatility and news delivers performance comparable to standard models at the daily horizon and improves forecasts at weekly and monthly horizons. The results reveal a clear horizon-dependent pattern. Implied volatility plays a central role in short-term predictions, while news-based variables become increasingly relevant at longer horizons. These findings highlight the complementary informational content of market expectations and textual data for understanding volatility dynamics.

Keywords: Volatility forecasting; news analysis; implied volatility; realized volatility; Brazilian equity market (search for similar items in EconPapers)
JEL-codes: C22 C53 C58 G17 (search for similar items in EconPapers)
Date: 2026-08-27
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.repec.eae.fea.usp.br/documentos/Gentini_Nakane_25WP.pdf (application/pdf)
Our link check indicates that this URL is bad, the error code is: 403 Forbidden

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:spa:wpaper:2026wpecon25

Ordering information: This working paper can be ordered from

Access Statistics for this paper

More papers in Working Papers, Department of Economics from University of São Paulo (FEA-USP) Contact information at EDIRC.
Bibliographic data for series maintained by Pedro Garcia Duarte ( this e-mail address is bad, please contact ).