Beyond Visual Realism: Toward Reliable Financial Time Series Generation

• URL: http://arxiv.org/abs/2601.12990v1
• Date: Mon, 19 Jan 2026 12:09:54 GMT
• Title: Beyond Visual Realism: Toward Reliable Financial Time Series Generation
• Abstract summary: Generative models for financial time series often create data that look realistic and even reproduce stylized facts such as fat tails or volatility clustering.<n>These apparent successes break down under trading backtests: models like GANs or WGAN-GP frequently collapse.<n>We identify the root cause in the neglect of financial asymmetry and rare tail events, which strongly affect market risk.
• Score: 10.458754867159508
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generative models for financial time series often create data that look realistic and even reproduce stylized facts such as fat tails or volatility clustering. However, these apparent successes break down under trading backtests: models like GANs or WGAN-GP frequently collapse, yielding extreme and unrealistic results that make the synthetic data unusable in practice. We identify the root cause in the neglect of financial asymmetry and rare tail events, which strongly affect market risk but are often overlooked by objectives focusing on distribution matching. To address this, we introduce the Stylized Facts Alignment GAN (SFAG), which converts key stylized facts into differentiable structural constraints and jointly optimizes them with adversarial loss. This multi-constraint design ensures that generated series remain aligned with market dynamics not only in plots but also in backtesting. Experiments on the Shanghai Composite Index (2004--2024) show that while baseline GANs produce unstable and implausible trading outcomes, SFAG generates synthetic data that preserve stylized facts and support robust momentum strategy performance. Our results highlight that structure-preserving objectives are essential to bridge the gap between superficial realism and practical usability in financial generative modeling.

Related papers

• High-Quality Synthetic Financial Time-Series using a GAN-Diffusion Framework [7.070661500694135]
  We present a quality-aware generative framework that combines two classes of generative methods.<n>We show how our GAN architecture can be incorporated into state-of-the-art diffusion models.<n>Our framework offers a lightweight and responsive solution for realistic stock market simulation.
  arXiv  Detail & Related papers  (2026-05-26T14:52:01Z)
• Consolidation or Adaptation? PRISM: Disentangling SFT and RL Data via Gradient Concentration [56.074760766965085]
  PRISM achieves a dynamics-aware framework that arbitrates data based on its degree of cognitive conflict with the model's existing knowledge.<n>Our findings suggest that disentangling data based on internal optimization regimes is crucial for scalable and robust agent alignment.
  arXiv  Detail & Related papers  (2026-01-12T05:43:20Z)
• Deep Generative Models for Synthetic Financial Data: Applications to Portfolio and Risk Modeling [0.0]
  Synthetic financial data provides a practical solution to the privacy, accessibility, and challenges that often constrain empirical research in quantitative finance.<n>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.
  arXiv  Detail & Related papers  (2025-12-25T22:28:32Z)
• T-TAMER: Provably Taming Trade-offs in ML Serving [32.526955555483354]
  We present a general framework, T-Tamer, which formalizes this setting as a multi-stage decision process.<n>Our main result shows that recall is both necessary and sufficient for achieving provable performance guarantees.<n>The results show that recall-based strategies consistently yield efficient accuracy-latency trade-offs.
  arXiv  Detail & Related papers  (2025-09-26T23:08:03Z)
• ProteuS: A Generative Approach for Simulating Concept Drift in Financial Markets [44.76567557906836]
  A fundamental problem in developing and validating adaptive algorithms is the lack of a ground truth in real-world financial data.<n>This paper introduces a novel framework, named ProteuS, for generating semi-synthetic financial time series with pre-defined structural breaks.<n>An analysis of the generated data confirms the complexity of the task, revealing significant overlap between the different market states.
  arXiv  Detail & Related papers  (2025-08-30T21:01:47Z)
• On Identifying Why and When Foundation Models Perform Well on Time-Series Forecasting Using Automated Explanations and Rating [7.375605655806626]
  Time-series forecasting models (TSFM) have evolved from classical statistical methods to sophisticated foundation models.<n>This work addresses concerns by combining traditional explainable AI (XAI) methods with Rating Driven Explanations (RDE)<n>We evaluate four distinct model architectures: ARIMA, Gradient Boosting, Chronos (time-series specific foundation model), Llama (general-purpose; both fine-tuned and base models)
  arXiv  Detail & Related papers  (2025-08-28T05:27:45Z)
• ACT-Tensor: Tensor Completion Framework for Financial Dataset Imputation [2.3404331106562677]
  We introduce an Adaptive, Cluster-based Temporal smoothing tensor completion framework (ACT-Tensor) for missing financial data panels.<n>ACT-Tensor consistently outperforms state-of-the-art benchmarks in terms of imputation accuracy across a range of missing data regimes.<n>Results show that ACT-Tensor not only reduces pricing errors but also significantly improves risk-adjusted returns of the constructed portfolio.
  arXiv  Detail & Related papers  (2025-08-03T17:28:57Z)
• Learning Time-Aware Causal Representation for Model Generalization in Evolving Domains [50.66049136093248]
  We develop a time-aware structural causal model (SCM) that incorporates dynamic causal factors and the causal mechanism drifts.<n>We show that our method can yield the optimal causal predictor for each time domain.<n>Results on both synthetic and real-world datasets exhibit that SYNC can achieve superior temporal generalization performance.
  arXiv  Detail & Related papers  (2025-06-21T14:05:37Z)
• A Theoretical Perspective: How to Prevent Model Collapse in Self-consuming Training Loops [55.07063067759609]
  High-quality data is essential for training large generative models, yet the vast reservoir of real data available online has become nearly depleted.<n>Models increasingly generate their own data for further training, forming Self-consuming Training Loops (STLs)<n>Some models degrade or even collapse, while others successfully avoid these failures, leaving a significant gap in theoretical understanding.
  arXiv  Detail & Related papers  (2025-02-26T06:18:13Z)
• STORM: A Spatio-Temporal Factor Model Based on Dual Vector Quantized Variational Autoencoders for Financial Trading [55.02735046724146]
  In financial trading, factor models are widely used to price assets and capture excess returns from mispricing.<n>We propose a Spatio-Temporal factOR Model based on dual vector quantized variational autoencoders, named STORM.<n>Storm extracts features of stocks from temporal and spatial perspectives, then fuses and aligns these features at the fine-grained and semantic level, and represents the factors as multi-dimensional embeddings.
  arXiv  Detail & Related papers  (2024-12-12T17:15:49Z)
• The Risk of Federated Learning to Skew Fine-Tuning Features and Underperform Out-of-Distribution Robustness [50.52507648690234]
  Federated learning has the risk of skewing fine-tuning features and compromising the robustness of the model. We introduce three robustness indicators and conduct experiments across diverse robust datasets. Our approach markedly enhances the robustness across diverse scenarios, encompassing various parameter-efficient fine-tuning methods.
  arXiv  Detail & Related papers  (2024-01-25T09:18:51Z)
• CasTGAN: Cascaded Generative Adversarial Network for Realistic Tabular Data Synthesis [0.4999814847776097]
  Generative adversarial networks (GANs) have drawn considerable attention in recent years for their proven capability in generating synthetic data. The validity of the synthetic data and the underlying privacy concerns represent major challenges which are not sufficiently addressed.
  arXiv  Detail & Related papers  (2023-07-01T16:52:18Z)
• Fairness Increases Adversarial Vulnerability [50.90773979394264]
  This paper shows the existence of a dichotomy between fairness and robustness, and analyzes when achieving fairness decreases the model robustness to adversarial samples. Experiments on non-linear models and different architectures validate the theoretical findings in multiple vision domains. The paper proposes a simple, yet effective, solution to construct models achieving good tradeoffs between fairness and robustness.
  arXiv  Detail & Related papers  (2022-11-21T19:55:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.