FCOC: A Fractal-Chaotic Co-driven Framework for Financial Volatility Forecasting

TL;DR

The paper presents FCOC, a novel framework combining fractal feature extraction and chaotic dynamics to significantly improve financial volatility forecasting accuracy and responsiveness.

Contribution

Introduces the FCOC framework integrating a fractal feature corrector and chaotic oscillation component, enhancing model fidelity and responsiveness in financial forecasting.

Findings

Improves performance of Transformer models on volatility prediction.

Achieves better risk-sensitive metrics on S&P 500 and DJI datasets.

Sets new benchmarks for risk-aware financial forecasting.

Abstract

This paper introduces the Fractal-Chaotic Oscillation Co-driven (FCOC) framework, a novel paradigm for financial volatility forecasting that systematically resolves the dual challenges of feature fidelity and model responsiveness. FCOC synergizes two core innovations: our novel Fractal Feature Corrector (FFC), engineered to extract high-fidelity fractal signals, and a bio-inspired Chaotic Oscillation Component (COC) that replaces static activations with a dynamic processing system. Empirically validated on the S\&P 500 and DJI, the FCOC framework demonstrates profound and generalizable impact. The framework fundamentally transforms the performance of previously underperforming architectures, such as the Transformer, while achieving substantial improvements in key risk-sensitive metrics for state-of-the-art models like Mamba. These results establish a powerful co-driven approach, where models are guided by superior theoretical features and powered by dynamic internal processors, setting a new benchmark for risk-aware forecasting.