Fusing Narrative Semantics for Financial Volatility Forecasting

TL;DR

This paper presents M2VN, a deep learning framework that fuses financial time series data with news text to improve volatility forecasting while addressing data alignment and look-ahead bias issues.

Contribution

The paper introduces M2VN, a novel multi-modal neural network that effectively combines structured and unstructured data for more accurate financial volatility predictions.

Findings

M2VN outperforms existing models in volatility forecasting accuracy.

The framework effectively aligns heterogeneous data modalities.

Mitigates look-ahead bias in financial modeling.

Abstract

We introduce M2VN: Multi-Modal Volatility Network, a novel deep learning-based framework for financial volatility forecasting that unifies time series features with unstructured news data. M2VN leverages the representational power of deep neural networks to address two key challenges in this domain: (i) aligning and fusing heterogeneous data modalities, numerical financial data and textual information, and (ii) mitigating look-ahead bias that can undermine the validity of financial models. To achieve this, M2VN combines open-source market features with news embeddings generated by Time Machine GPT, a recently introduced point-in-time LLM, ensuring temporal integrity. An auxiliary alignment loss is introduced to enhance the integration of structured and unstructured data within the deep learning architecture. Extensive experiments demonstrate that M2VN consistently outperforms existing baselines, underscoring its practical value for risk management and financial decision-making in dynamic markets.