Beyond Visual Realism: Toward Reliable Financial Time Series Generation

TL;DR

This paper introduces SFAG, a novel generative model for financial time series that incorporates stylized facts as structural constraints, improving the realism and practical utility of synthetic data in trading backtests.

Contribution

We propose SFAG, a new GAN-based framework that enforces stylized facts as differentiable constraints, enhancing the stability and realism of generated financial data.

Findings

SFAG preserves stylized facts better than baseline GANs.

Synthetic data from SFAG support more robust trading strategies.

Baseline GANs often produce unrealistic trading outcomes.

Abstract

Generative models for financial time series often create data that look realistic and even reproduce stylized facts such as fat tails or volatility clustering. However, these apparent successes break down under trading backtests: models like GANs or WGAN-GP frequently collapse, yielding extreme and unrealistic results that make the synthetic data unusable in practice. We identify the root cause in the neglect of financial asymmetry and rare tail events, which strongly affect market risk but are often overlooked by objectives focusing on distribution matching. To address this, we introduce the Stylized Facts Alignment GAN (SFAG), which converts key stylized facts into differentiable structural constraints and jointly optimizes them with adversarial loss. This multi-constraint design ensures that generated series remain aligned with market dynamics not only in plots but also in backtesting. Experiments on the Shanghai Composite Index (2004--2024) show that while baseline GANs produce unstable and implausible trading outcomes, SFAG generates synthetic data that preserve stylized facts and support robust momentum strategy performance. Our results highlight that structure-preserving objectives are essential to bridge the gap between superficial realism and practical usability in financial generative modeling.