cs.LGNov 5, 2026

Scenario Augmentation for Rare Financial Events via Multimodal Latent Diffusion

Authors: Mahdi Arab Loodaricheh, Anita Raja, Indranil SenGupta

Organizations: The Graduate Center, CUNY · Hunter College, CUNY

Abstract

Extreme market movements are scarce, heterogeneous, and difficult to learn from imbalanced historical data. We study whether generative augmentation can improve the representation and classification of CVaR-labeled rare financial windows while retaining the complementary structure exposed by different financial representations. Each market window is expressed through three aligned modalities: structured market variables, a spatial image transformation, and a sequence of portfolio returns. Separate variational autoencoders map the modalities to compact latent codes, and a class-conditional diffusion model learns their joint latent distribution. Conditional Value-at-Risk (CVaR) provides a risk-aware definition of rare windows and directs generation toward the minority regime. Across four window lengths on U.S. technology equities, the resulting synthetic samples improve fidelity and support relative to tabular diffusion baselines. An XGBoost classifier trained with real and generated samples attains AUCs of 0.953 - 0.960, exceeding both tabular generators and the corresponding real-only baselines. These results show that multimodal latent generation can provide useful synthetic stress scenarios for data-scarce financial risk models.

Figures & tables

Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Improving Machine Learning Performance with Synthetic Augmentation

    Apr 16, 2026Mel Sohm, Charles Dezons, Sami Sellami +2Synthetic Data AugmentationQuantitative Finance

  2. High-Quality Synthetic Financial Time-Series using a GAN-Diffusion Framework

    May 26, 2026Giuseppe Masi, Andrea Coletta, Novella BartoliniSynthetic Data GenerationTime Series Generation

  3. Few-Shot Synthetic Data Generation with Diffusion Models for Downstream Vision Tasks

    May 12, 2026Daniil Dushenev, Nazariy Karpov, Daniil Zinovjev +2Class-Imbalanced LearningSynthetic Data Augmentation