Deep Generative Models for Synthetic Financial Data: Applications to Portfolio and Risk Modeling

TL;DR

This paper explores deep generative models, specifically TimeGAN and VAEs, for creating realistic synthetic financial data to improve privacy, accessibility, and reproducibility in portfolio and risk modeling.

Contribution

It demonstrates the effectiveness of TimeGAN and VAEs in generating synthetic financial data that closely mimics real market behavior for practical financial applications.

Findings

TimeGAN produces data with realistic distribution and temporal patterns.

Synthetic data leads to similar portfolio metrics as real data.

VAEs offer stable training but smooth out extreme market movements.

Abstract

Synthetic financial data provides a practical solution to the privacy, accessibility, and reproducibility challenges that often constrain empirical research in quantitative finance. This paper investigates the use of deep generative models, specifically Time-series Generative Adversarial Networks (TimeGAN) and Variational Autoencoders (VAEs) to generate realistic synthetic financial return series for portfolio construction and risk modeling applications. Using historical daily returns from the S and P 500 as a benchmark, we generate synthetic datasets under comparable market conditions and evaluate them using statistical similarity metrics, temporal structure tests, and downstream financial tasks. The study shows that TimeGAN produces synthetic data with distributional shapes, volatility patterns, and autocorrelation behaviour that are close to those observed in real returns. When applied to mean--variance portfolio optimization, the resulting synthetic datasets lead to portfolio weights, Sharpe ratios, and risk levels that remain close to those obtained from real data. The VAE provides more stable training but tends to smooth extreme market movements, which affects risk estimation. Finally, the analysis supports the use of synthetic datasets as substitutes for real financial data in portfolio analysis and risk simulation, particularly when models are able to capture temporal dynamics. Synthetic data therefore provides a privacy-preserving, cost-effective, and reproducible tool for financial experimentation and model development.