Regime-aware financial volatility forecasting via in-context learning

TL;DR

This paper presents a novel regime-aware in-context learning framework using large language models to adapt financial volatility forecasts to changing market regimes without fine-tuning, improving accuracy during volatile periods.

Contribution

It introduces a regime-aware in-context learning approach with an oracle-guided demonstration construction, enabling LLMs to adapt to market regimes for volatility prediction.

Findings

Outperforms classical volatility forecasting methods.

Achieves better accuracy during high-volatility periods.

Demonstrates effectiveness across multiple financial datasets.

Abstract

This work introduces a regime-aware in-context learning framework that leverages large language models (LLMs) for financial volatility forecasting under nonstationary market conditions. The proposed approach deploys pretrained LLMs to reason over historical volatility patterns and adjust their predictions without parameter fine-tuning. We develop an oracle-guided refinement procedure that constructs regime-aware demonstrations from training data. An LLM is then deployed as an in-context learner that predicts the next-step volatility from the input sequence using demonstrations sampled conditional to the estimated market label. This conditional sampling strategy enables the LLM to adapt its predictions to regime-dependent volatility dynamics through contextual reasoning alone. Experiments with multiple financial datasets show that the proposed regime-aware in-context learning framework outperforms both classical volatility forecasting approaches and direct one-shot learning, especially during high-volatility periods.