Financial models improve by tracking volatility clustering patterns
Volatility-Clustering Adaptation for Financial Time Series
Machine Learning
Summary
Predicting exact price changes in finance is tough, but big price swings tend to happen in groups, making calm and busy periods. The authors show that simply training models to guess the next price isn’t enough for good forecasts. They propose a new technique called Volatility-Clustering Adaptation that teaches models to pay attention to these clusters of big changes. Their method helps models better match the real patterns of market ups and downs, improving forecasting accuracy especially by reducing unpredictable errors.
What this means in practice
- •For quantitative traders: Enhance financial forecasting models to better capture clustered volatility for improved trading strategy performance.
- •For risk management teams: Improve risk estimates by integrating models that consider volatility clustering in financial time series.
Authors
Manh Nguyen, Minh Hoang Nguyen, Huu Hiep Nguyen, Van Dai Do, Hung Le
Abstract
Time-series foundation models are increasingly adapted to new domains through fine-tuning on target data, under the implicit assumption that more target data yields better forecasts. We show that this assumption can fail in financial forecasting, where individual price changes are difficult to predict, but large moves tend to cluster, creating alternating calm and turbulent periods. Using financial foundation models trained on price bars of open, high, low, close, and volume, we argue that adapting to financial domains requires training signals beyond next-token prediction. We introduce Volatility-Clustering Adaptation (VCA), which augments next-token cross-entropy with a differentiable penalty on the autocorrelation of squared returns, the standard statistical signature of volatility clustering. This additional objective provides a multi-step training signal by matching the resulting dependence structure of autoregressive rollouts to those of the realized future. Across three asset sets and two evaluation conventions, VCA improves adaptation over the pre-trained model, with the strongest gains under the primary evaluation (\textsc{fore}), driven primarily by reduced variance error. Overall, our results suggest that effective financial adaptation requires objectives that capture domain-specific temporal structure beyond token-level prediction.