Regime-aware financial volatility forecasting via in-context learning

• URL: http://arxiv.org/abs/2603.10299v1
• Date: Wed, 11 Mar 2026 00:47:27 GMT
• Title: Regime-aware financial volatility forecasting via in-context learning
• Abstract summary: This work introduces a regime-aware in-context learning framework that leverages large language models (LLMs) for financial volatility forecasting under nonstationary market conditions.<n> 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.
• Score: 19.089657251243196
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Making Alternative Data Work: Context-Augmented LLMs for Financial Forecasting [66.81020766645811]
  Large language models (LLMs) can interpret instructions, learn from in-context examples, and generate predictions.<n>We propose a two-agent framework that first identifies the firms for which each alternative data channel is likely to be informative.<n>We evaluate the framework across four commercial alternative data channels.
  arXiv  Detail & Related papers  (2026-09-10T14:27:25Z)
• Reasoning through Verifiable Forecast Actions: Consistency-Grounded RL for Financial LLMs [34.87727677131385]
  We introduce StockR1, a time-series-enhanced LLM that unifies stock forecasting and financial reasoning through a verifiable forecast action.<n>Based on a tool-call design, the model first emits a forecast action, which is a structured and interpretable representation of its qualitative market outlook.<n>We optimize the full pipeline with reinforcement learning, where rewards jointly reflect answer validity, forecast accuracy, and consistency between generated actions and observed time-series dynamics.
  arXiv  Detail & Related papers  (2026-05-21T04:09:16Z)
• LEAF: A Living Benchmark for Event-Augmented Forecasting [78.94019460534442]
  LEAF is the first living benchmark for event-augmented forecasting tasks.<n>We evaluate state-of-the-art proprietary and open-weight LLMs.<n>We find that LLMs achieve better performance on equities they confidently identify as more predictable.
  arXiv  Detail & Related papers  (2026-05-09T03:17:59Z)
• Context-Integrated Adversarial Learning for Predictive Modelling of Stock Price Dynamics [0.0]
  This paper introduces a context-sensitive adversarial learning model to predict equity prices.<n>The architecture uses adversarial training to model future price movements and incorporates contextual sentiment features derived from financial textual data.<n> Empirical evaluation of a sample of U.S. equities testifies that the presented approach outperforms the traditional ARIMA and LSTM baselines in a range of measures of error.
  arXiv  Detail & Related papers  (2026-04-13T18:51:01Z)
• $φ$-DPO: Fairness Direct Preference Optimization Approach to Continual Learning in Large Multimodal Models [58.217707070069885]
  This paper presents a novel Fairness Direct Preference Optimization (FaiDPO or $$-DPO) framework for continual learning in LMMs.<n>We first propose a new continual learning paradigm based on Direct Preference Optimization (DPO) to mitigate catastrophic forgetting by aligning learning with pairwise preference signals.<n> Extensive experiments and ablation studies show the proposed $$-DPO achieves State-of-the-Art performance across multiple benchmarks.
  arXiv  Detail & Related papers  (2026-02-26T04:14:33Z)
• Beyond Naïve Prompting: Strategies for Improved Zero-shot Context-aided Forecasting with LLMs [57.82819770709032]
  Large language models (LLMs) can be effective context-aided forecasters via na"ive direct prompting.<n>ReDP improves interpretability by eliciting explicit reasoning traces, allowing us to assess the model's reasoning over the context.<n>CorDP leverages LLMs solely to refine existing forecasts with context, enhancing their applicability in real-world forecasting pipelines.<n> IC-DP proposes embedding historical examples of context-aided forecasting tasks in the prompt, substantially improving accuracy even for the largest models.
  arXiv  Detail & Related papers  (2025-08-13T16:02:55Z)
• From predictions to confidence intervals: an empirical study of conformal prediction methods for in-context learning [4.758643223243787]
  We propose a method based on conformal prediction to construct prediction intervals with guaranteed coverage.<n>While traditional conformal methods are computationally expensive due to repeated model fitting, we exploit ICL to efficiently generate confidence intervals in a single forward pass.<n>Our empirical analysis compares this approach against ridge regression-based conformal methods, showing that conformal prediction with in-context learning (CP with ICL) achieves robust and scalable uncertainty estimates.
  arXiv  Detail & Related papers  (2025-04-22T09:11:48Z)
• BreakGPT: Leveraging Large Language Models for Predicting Asset Price Surges [55.2480439325792]
  This paper introduces BreakGPT, a novel large language model (LLM) architecture adapted specifically for time series forecasting and the prediction of sharp upward movements in asset prices. We showcase BreakGPT as a promising solution for financial forecasting with minimal training and as a strong competitor for capturing both local and global temporal dependencies.
  arXiv  Detail & Related papers  (2024-11-09T05:40:32Z)
• Diffusion Variational Autoencoder for Tackling Stochasticity in Multi-Step Regression Stock Price Prediction [54.21695754082441]
  Multi-step stock price prediction over a long-term horizon is crucial for forecasting its volatility. Current solutions to multi-step stock price prediction are mostly designed for single-step, classification-based predictions. We combine a deep hierarchical variational-autoencoder (VAE) and diffusion probabilistic techniques to do seq2seq stock prediction. Our model is shown to outperform state-of-the-art solutions in terms of its prediction accuracy and variance.
  arXiv  Detail & Related papers  (2023-08-18T16:21:15Z)
• Can ChatGPT Forecast Stock Price Movements? Return Predictability and Large Language Models [48.87381259980254]
  We document the capability of large language models (LLMs) like ChatGPT to predict stock market reactions from news headlines without direct financial training.<n>Using post-knowledge-cutoff headlines, GPT-4 captures initial market responses, achieving approximately 90% portfolio-day hit rates for the non-tradable initial reaction.
  arXiv  Detail & Related papers  (2023-04-15T19:22:37Z)
• Deep Learning Enhanced Realized GARCH [6.211385208178938]
  We propose a new approach to volatility modeling by combining deep learning (LSTM) and realized volatility measures. This LSTM-enhanced realized GARCH framework incorporates and distills modeling advances from financial econometrics, high frequency trading data and deep learning.
  arXiv  Detail & Related papers  (2023-02-16T00:20:43Z)
• Adaptive Learning on Time Series: Method and Financial Applications [0.0]
  We use Adaptive Learning to forecast S&P 500 returns across multiple forecast horizons. We find that Adaptive Learning models are on par with, if not better than, the best of the parametric models a posteriori. We present a financial application of the learning results and an interpretation of the learning regime during the 2020 market crash.
  arXiv  Detail & Related papers  (2021-10-21T13:59:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.