Extreme Volatility Warning under Label Scarcity via Multi-Source Anomaly Fusion

2026-07-26

AI Summary

This study addresses the instability of supervised models in forecasting extreme market volatility, a challenge arising from label scarcity, non-stationarity of events, and exogenous shocks. To overcome these limitations, the authors propose AAMSF, a semi-supervised framework that eschews complex supervised modeling in favor of lightweight anomaly scoring derived from heterogeneous data sources—including market indicators, GDELT event records, and Chinese-English news—and reliably fuses these scores via Ridge regression. They further introduce a temporal extension, T-AAMSF, which accumulates multi-day anomalies to enhance early-warning capability. Evaluated on the CSI 300 dataset, AAMSF achieves an AUC-ROC of 0.680, substantially outperforming unsupervised (0.630) and neural network baselines (0.588); T-AAMSF further improves performance, attaining a PR-AUC of 0.291, thereby demonstrating the method’s effectiveness and robustness.

Abstract

Early warning of extreme market volatility is central to financial risk management, but actionable events are rare, nonstationary, and often triggered by exogenous information shocks. In our CSI~300 setting, only $\sim$80 positive samples are observed across 791 training days, making heavily supervised multi-source models unstable. We first analyze a 100K-parameter hierarchical text-signal fusion model (HTSF) and find that added parameterization hurts in this low-label regime. Motivated by this failure, we propose \textbf{AAMSF} (Anomaly-Augmented Multi-Signal Fusion), a semisupervised framework that combines Isolation Forest anomaly scores over market indicators, GDELT events, Chinese financial news, and English media with lightweight Ridge score fusion. We further introduce \textbf{T-AAMSF}, a temporal extension for multi-day anomaly accumulation. On CSI~300 (2018--2023), AAMSF achieves test AUC-ROC \textbf{0.680}, outperforming the strongest unsupervised baseline (0.630) and neural baseline (0.588), while T-AAMSF improves PR-AUC to 0.291. Ablations reveal strong source asymmetry: GDELT and domestic financial news provide complementary risk signals, whereas English media consistently reduces performance, and learned weighting is unreliable under validation noise. These results suggest an empirical design principle for label-scarce financial risk warning: robust anomaly geometry and source reliability can matter more than supervised representation capacity.

Problem

• extreme volatility
• label scarcity
• financial risk warning
• anomaly detection
• multi-source fusion

Innovation

• anomaly detection
• multi-source fusion
• label scarcity
• financial risk warning
• semi-supervised learning