---
title: Multilingual Textual Signals and Realized Volatility Forecasting: A Hybrid Transformer-HAR-X Approach Applied to the S&P 500 and the MASI
url: https://www.ml-quant.com/papers/repec/hal-journl-hal-05723648/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-11-06
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
identifier: RePEc:hal:journl:hal-05723648
source_url: https://econpapers.repec.org/RePEc:hal:journl:hal-05723648
featured: 2026-11-06
citations: unknown
topic: ML & AI Methods
---


# Multilingual Textual Signals and Realized Volatility Forecasting: A Hybrid Transformer-HAR-X Approach Applied to the S&P 500 and the MASI

A hybrid FinBERT-HAR-X framework using multilingual news reduces S&P 500 volatility forecast error by 21% and improves realized Sharpe ratios out of sample.

- Source: https://econpapers.repec.org/RePEc:hal:journl:hal-05723648
- Identifier: RePEc:hal:journl:hal-05723648
- Released: 2026-11-02
- First featured: Quant Letter No. 138 (2026-11-06): https://www.ml-quant.com/issues/2026-11-06/
- Citations (Semantic Scholar): not tracked
- Published in: not yet
- Topic: ML & AI Methods
- Authors: Sara Boughanou, Adil El Marhoum

## Related

- [Transformer for Times Series: an Application to the S&P500](https://www.ml-quant.com/papers/arxiv/2403.02523/): The research investigates the use of transformer models in financial time series prediction, showing promising results with synthetic data and insightful findings on S&P500 data volatility prediction.
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://www.ml-quant.com/papers/arxiv/2312.00752/): Sequence Modeling: Mamba, a neural network architecture that doesn't use attention or MLP blocks, provides faster inference and better performance in language, audio, and genomics than Transformers.
- [Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality](https://www.ml-quant.com/papers/arxiv/2405.21060/): The research identifies a link between state-space models and Transformers in deep learning, leading to the creation of a faster language modeling architecture, Mamba-2.
- [Octo: An Open-Source Generalist Robot Policy](https://www.ml-quant.com/papers/arxiv/2405.12213/): Octo is a large transformer-based policy for robotic manipulation, trained on a vast dataset, that can be instructed via language or images and adapted to new domains.
- [Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction](https://www.ml-quant.com/papers/arxiv/2404.02905/): The article discusses Visual AutoRegressive modeling (VAR), a new image learning method that outperforms diffusion transformers in terms of speed, image quality, and scalability.
- [PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis](https://www.ml-quant.com/papers/arxiv/2310.00426/): PIXART-$\alpha$, a Transformer-based text-to-image model, generates high-quality images at a low cost, reducing CO2 emissions and offering a cost-effective solution for the AIGC community.