---
title: Realised Volatility Forecasting with Word Embedding
url: https://www.ml-quant.com/papers/ssrn/4754276/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-09-26
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
identifier: SSRN 4754276
source_url: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4754276
featured: 2024-03-13
citations: unknown
topic: Derivatives & Volatility
---


# Realised Volatility Forecasting with Word Embedding

The study presents FinText, a tool that enhances volatility forecasts using business news archives and identifies key phrases impacting volatility.

- Source: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4754276
- Identifier: SSRN 4754276
- Released: 2024-03-10
- First featured: Quant Letter No. 40 (2024-03-13): https://www.ml-quant.com/issues/2024-03-13/
- Citations (Semantic Scholar): not tracked
- Published in: not yet
- Topic: Derivatives & Volatility

## Related

- [Realised Volatility Forecasting: Machine Learning via Financial Word Embedding](https://www.ml-quant.com/papers/arxiv/2108.00480/): A new NLP framework shows that adding news text can improve stock volatility forecasting, particularly during volatile times, when combined with standard models.
- [TSMixer and Realized Volatility Prediction](https://www.ml-quant.com/papers/ssrn/4713756/): Stock Volatility Forecasting with Neural Networks: The TSMixer neural network model has proven to be more effective than traditional models in predicting stock market volatility, indicating a possible shift towards simpler models in the future.
- [SpotV2Net: Multivariate Intraday Spot Volatility Forecasting via Vol-of-Vol-Informed Graph Attention Networks](https://www.ml-quant.com/papers/arxiv/2401.06249/): Intraday Volatility Forecasting: The article introduces SpotV2Net, a new model for predicting intraday spot volatility using a Graph Attention Network, which has shown better accuracy in predicting Dow Jones Industrial Average index prices.
- [Harnessing Volatility Cascades with Ensemble Learning](https://www.ml-quant.com/papers/ssrn/4682793/): A modification to the base learner in bootstrap aggregation and boosting can significantly improve predictive accuracy in volatility forecasting, addressing substantial errors from parameter estimation.
- [TimesNet for Realized Volatility Prediction](https://www.ml-quant.com/papers/ssrn/4660025/): The study shows that the TimesNet model is effective in predicting stock volatility, particularly during extreme market movements, making it a strong neural network benchmark in volatility research.
- [Stock Volatility Prediction Based on Transformer Model Using Mixed-Frequency Data](https://www.ml-quant.com/papers/arxiv/2309.16196/): A new model combining macroeconomic indicators, stock technical indicators, and Baidu search indices significantly improves stock volatility prediction, reducing error from 1.00 to 0.86.