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

Paper: arXiv 2610.24544

Authors: Yifan He

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.

Complexity vs Empirical Score

• Math Complexity: 6.5/10
• Empirical Rigor: 8.0/10
• Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: This paper exhibits a strong blend of advanced mathematical concepts, particularly in the TimeGAN and Rachev-ratio optimization, coupled with a highly rigorous empirical evaluation. The detailed experimental design, transaction costs, and multiple comparison policies demonstrate a robust approach to testing the proposed methodology.

Research Flowchart

  flowchart TD
    A[Research Goal: Evaluate TimeGAN Scenarios for Rachev-Ratio Portfolio Optimization] --> B{Methodology: Compare Historical, Replacement & Hybrid Policies};
    B --> C[Data/Inputs: 12 ETFs, 5 Training Seeds, Delayed Execution, Transaction Costs];
    C --> D{Computational Process: TimeGAN Scenario Generation & Rachev-Ratio Optimization};
    D --> E[Key Finding 1: Generated Scenarios Understate Volatility, Tail Losses & Distort Dependence];
    E --> F[Key Finding 2: Higher-Mass Hybrids Earn Larger Average Returns in Some Configurations];
    F --> G[Key Finding 3: TimeGAN Means Exceed Resampling Controls, But No Significant Outperformance for Paired Returns/Sharpe];
    G --> H[Key Finding 4: Replacement Raises Turnover & is Sensitive to Objective's Denominator Floor, Illustrating Financial Model Risk];

Cited References (20)

1. Deep Generative Models for Synthetic Financial Data: Applications to Portfolio and Risk Modeling — → 2512.21798
2. Synthetic Financial Data Generation for Enhanced Financial Modelling — → 2512.21791
3. Generative modelling of financial time series with structured noise and MMD-based signature learning — → 2407.19848
4. A modified CTGAN-plus-features-based method for optimal asset allocation — → 2302.02269
5. Pricing and Liquidity of Fixed Income ETFs in the Covid-19 Virus Crisis of 2020 (2020) — link
6. Quant GANs: deep generation of financial time series (2019) — link
7. Generative adversarial networks for financial trading strategies fine-tuning and combination (2019) — link
8. Optimal Versus Naive Diversification: How Inefficient is the 1/N Portfolio Strategy? (2009) — link

4 of 20 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.