Rachev-Ratio Portfolio Optimization with TimeGAN Scenarios: Replacement versus Supplementation

By Yifan He

Rating

1741
Battle Count: 53

Relevance

8/10
Highly relevant for practitioners using generative AI for scenario generation in portfolio construction. It highlights the risks of using imperfect synthetic data for tail-sensitive objectives like the Rachev ratio and emphasizes the importance of transaction costs and turnover.

Implementation Complexity

7/10
Requires implementing a TimeGAN architecture (GRU-based), handling rolling window training, and solving a non-convex, non-smooth optimization problem (Rachev ratio) with specific numerical constraints and fractional tail weighting.

Reproducibility

3/5
The paper mentions accompanying code and a REPRODUCIBILITY.txt file that documents preprocessing, training, and optimization. It specifies software versions (PyTorch, SciPy) and random seeds. However, a direct public GitHub URL is not explicitly provided in the text extract, though the existence of the code package is asserted. Capped at 3/5 by Everscope: the paper links no public code repository.

Abstract

This study evaluates the reliability and investment consequences of scenarios from a specified time-series generative adversarial network (TimeGAN) in Rachev-ratio portfolio allocation. Using 12 exchange-traded funds, we compare historical, replacement and hybrid policies across five training seeds with delayed execution and transaction costs. Synthetic probability mass varies independently of draw count under a fixed training protocol; optimal generator fidelity is not assumed. Generated scenarios understate volatility and tail losses and distort dependence. Limited longer-training diagnostics improve reconstruction loss without improving cross-asset correlation accuracy. Higher-mass hybrids earn larger average net returns in some configurations, but all conditional generated-versus-historical return intervals include zero at the reference block length. Full-period TimeGAN means exceed resampling controls, while direct paired return, Sharpe and realized-tail-ratio intervals include zero. Replacement raises turnover and is sensitive to the modified objective's denominator floor; changing that floor does not uniformly improve realized downside risk. Exploratory generation-error associations do not identify a causal investment-performance channel. The results illustrate financial model risk from the interaction of imperfect scenarios and a tail-sensitive allocation criterion, supporting joint evaluation of fidelity, numerical behavior and realized outcomes within the tested implementation.

Links

arXiv:2610.24544 ยท Paper rankings

The interactive Everscope explorer (charts, battles, favorites) loads below.