Realised Volatility Forecasting: Machine Learning via Financial Word Embedding
Computational Finance
2026-04-15 v6 Computation and Language
Machine Learning
Abstract
We examine whether news can improve realised volatility forecasting using a modern yet operationally simple NLP framework. News text is transformed into embedding-based representations, and forecasts are evaluated both as a standalone, news-only model and as a complement to standard realised volatility benchmarks. In out-of-sample tests on a cross-section of stocks, news contains useful predictive information, with stronger effects for stock-related content and during high volatility days. Combining the news-based signal with a leading benchmark yields consistent improvements in statistical performance and economically meaningful gains, while explainability analysis highlights the news themes most relevant for volatility.
Keywords
Cite
@article{arxiv.2108.00480,
title = {Realised Volatility Forecasting: Machine Learning via Financial Word Embedding},
author = {Eghbal Rahimikia and Stefan Zohren and Ser-Huang Poon},
journal= {arXiv preprint arXiv:2108.00480},
year = {2026}
}