Improving Machine Learning Performance with Synthetic Augmentation

TL;DR

This paper analyzes the statistical effects of synthetic data augmentation in financial machine learning, revealing it can reduce variance but may introduce bias, depending on the regime.

Contribution

It formalizes the impact of synthetic augmentation as a bias-variance trade-off and introduces a null augmentation and permutation test to evaluate informational gains.

Findings

Synthetic augmentation benefits variance-dominant regimes like volatility forecasting.

It deteriorates performance in bias-dominant settings such as directional prediction.

Rare-regime targeting can improve domain-specific metrics but may conflict with permutation inference.

Abstract

Synthetic augmentation is increasingly used to mitigate data scarcity in financial machine learning, yet its statistical role remains poorly understood. We formalize synthetic augmentation as a modification of the effective training distribution and show that it induces a structural bias--variance trade-off: while additional samples may reduce estimation error, they may also shift the population objective whenever the synthetic distribution deviates from regions relevant under evaluation. To isolate informational gains from mechanical sample-size effects, we introduce a size-matched null augmentation and a finite-sample, non-parametric block permutation test that remains valid under weak temporal dependence. We evaluate this framework in both controlled Markov-switching environments and real financial datasets, including high-frequency option trade data and a daily equity panel. Across generators spanning bootstrap, copula-based models, variational autoencoders, diffusion models, and TimeGAN, we vary augmentation ratio, model capacity, task type, regime rarity, and signal-to-noise. We show that synthetic augmentation is beneficial only in variance-dominant regimes, such as persistent volatility forecasting-while it deteriorates performance in bias-dominant settings, including near-efficient directional prediction. Rare-regime targeting can improve domain-specific metrics but may conflict with unconditional permutation inference. Our results provide a structural perspective on when synthetic data improves financial learning performance and when it induces persistent distributional distortion.