# Synthetic Data for Portfolios: A Throw of the Dice Will Never Abolish Chance

arXiv: https://arxiv.org/abs/2501.03993 · HTML: https://mlsanity.com/paper/2501.03993/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 108 references that are in the map.
- First posted on arXiv 7 Jan 2025.

## Builds on (most cited first, 30 of 31)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [Wasserstein GAN](https://mlsanity.com/paper/1701.07875/) (2017)
- [Pros and Cons of GAN Evaluation Measures](https://mlsanity.com/paper/1802.03446/) (2018)
- [Prediction-Powered Inference](https://mlsanity.com/paper/2301.09633/) (2023)
- [TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generation](https://mlsanity.com/paper/2111.08095/) (2021)
- [Quant GANs: Deep Generation of Financial Time Series](https://mlsanity.com/paper/1907.06673/) (2019)
- [FinDiff: Diffusion Models for Financial Tabular Data Generation](https://mlsanity.com/paper/2309.01472/) (2023)
- [A Data-driven Market Simulator for Small Data Environments](https://mlsanity.com/paper/2006.14498/) (2020)
- [The landscape of the spiked tensor model](https://mlsanity.com/paper/1711.05424/) (2017)
- [Deep Hedging: Learning to Simulate Equity Option Markets](https://mlsanity.com/paper/1911.01700/) (2019)
- [Conditional Sig-Wasserstein GANs for Time Series Generation](https://mlsanity.com/paper/2006.05421/) (2020)
- [Generative Adversarial Networks for Financial Trading Strategies Fine-Tuning and Combination](https://mlsanity.com/paper/1901.01751/) (2019)
- [Synthetic Data Applications in Finance](https://mlsanity.com/paper/2401.00081/) (2023)
- [Regurgitative Training: The Value of Real Data in Training Large Language Models](https://mlsanity.com/paper/2407.12835/) (2024)
- [Understanding GANs: the LQG Setting](https://mlsanity.com/paper/1710.10793/) (2017)
- [Decision-Aware Conditional GANs for Time Series Data](https://mlsanity.com/paper/2009.12682/) (2020)
- [Style Transfer with Time Series: Generating Synthetic Financial Data](https://mlsanity.com/paper/1906.03232/) (2019)
- [Deep Generative Modeling for Financial Time Series with Application in VaR: A Comparative Review](https://mlsanity.com/paper/2401.10370/) (2024)
- [Markowitz Portfolio Construction at Seventy](https://mlsanity.com/paper/2401.05080/) (2024)
- [Simulating financial time series using attention](https://mlsanity.com/paper/2207.00493/) (2022)
- [Improving the Robustness of Trading Strategy Backtesting with Boltzmann Machines and Generative Adversarial Networks](https://mlsanity.com/paper/2007.04838/) (2020)
- [A Modified CTGAN-Plus-Features Based Method for Optimal Asset Allocation](https://mlsanity.com/paper/2302.02269/) (2023)

## Built on by (most cited first, 4 of 4)

- [SBBTS: A Unified Schr"odinger-Bass Framework for Synthetic Financial Time Series](https://mlsanity.com/paper/2604.07159/) (2026)
- [Nested Optimal Transport Distances](https://mlsanity.com/paper/2509.06702/) (2025)
- [Factor-Based Conditional Diffusion Model for Contextual Portfolio Optimization](https://mlsanity.com/paper/2509.22088/) (2025)
- [Covariance Shrinkage via Stochastic Interpolation](https://mlsanity.com/paper/2606.07382/) (2026)

## Abstract (arXiv)

Simulation methods have always been instrumental in finance, and data-driven methods with minimal model specification, commonly referred to as generative models, have attracted increasing attention, especially after the success of deep learning in a broad range of fields. However, the adoption of these models in financial applications has not matched the growing interest, probably due to the unique complexities and challenges of financial markets. This paper contributes to a deeper understanding of the limitations of generative models, particularly in portfolio and risk management. To this end, we begin by presenting theoretical results on the importance of initial sample size, and point out the potential pitfalls of generating far more data than originally available. We then highlight the inseparable nature of model development and the desired uses by touching on a paradox: usual generative models inherently care less about what is important for constructing portfolios (in particular the long-short ones). Based on these findings, we propose a pipeline for the generation of multivariate returns that meets conventional evaluation standards on a large universe of US equities while being compliant with stylized facts observed in asset returns and turning around the pitfalls we previously identified. Moreover, we insist on the need for more accurate evaluation methods, and suggest, through an example of mean-reversion strategies, a method designed to identify poor models for a given application based on regurgitative training, i.e. retraining the model using the data it has itself generated, which is commonly referred to in statistics as identifiability.