---
title: Improving Portfolio Construction with Synthetic Time Series Data
url: https://www.ml-quant.com/papers/ssrn/4809931/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-09-26
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
identifier: SSRN 4809931
source_url: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4809931
featured: 2024-05-01
citations: 0
topic: Portfolio & Allocation
---


# Improving Portfolio Construction with Synthetic Time Series Data

A deep generative model can create high-quality, correlation-aware synthetic financial time series, useful in a GAN-assisted risk-based portfolio construction method.

- Source: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4809931
- Identifier: SSRN 4809931
- Released: 2024-04-27
- First featured: Quant Letter No. 47 (2024-05-01): https://www.ml-quant.com/issues/2024-05-01/
- Citations (Semantic Scholar): 0
- Published in: not yet
- Topic: Portfolio & Allocation

## Related

- [A monotone numerical integration method for mean-variance portfolio optimization under jump-diffusion models](https://www.ml-quant.com/papers/arxiv/2309.05977/): The research introduces an efficient numerical integration method for portfolio optimization, demonstrating its computational efficiency and accuracy, and its convergence to the unique solution of the optimization problem.
- [Synthetic data for portfolios: a throw of the dice will never abolish chance](https://www.ml-quant.com/papers/arxiv/2501.03993/): The paper highlights the shortcomings of generative models in finance, suggesting a method for generating multivariate returns that meets standard evaluations and aligns with observed asset returns.
- [Dynamic data generation and dynamic portfolio selection: an application of a score-based diffusion model](https://www.ml-quant.com/papers/arxiv/2507.09916/): A model-free approach using generative diffusion models and a policy gradient algorithm has been suggested for dynamic mean-variance portfolio selection, outperforming the Markowitz portfolio and S&P 500.
- [Portfolio Construction and Risk Management](https://www.ml-quant.com/papers/ssrn/4807200/): A crowdfunding campaign is underway to fund a book on portfolio construction and risk management, featuring a guide to a next-generation investment framework and Python code.
- [Bond Portfolio Optimization at Life Insurance Companies: Duration Spread Ratio Optimization vs. Mean-Variance Optimization](https://www.ml-quant.com/papers/ssrn/4825814/): The research compares the effects of integrating credit risk and interest rate risk in bond portfolio optimization with traditional risk measures, introducing a new approach called Duration Spread Ratio (DSR) optimization that outperforms in all scenarios.
- [ESG and Behavioral Finance: Why ESG Investing Is Primarily a Psychological Phenomenon](https://www.ml-quant.com/papers/ssrn/4786610/): A Psychological Phenomenon: The study expands traditional portfolio selection and asset pricing theory to include ESG investing, introducing two behavioral innovations related to investor preferences and biased judgments about ESG impact and return distributions.