用因果模型生成金融反事实数据，提升风险评估准确性。
Towards Causal Market Simulators
- 结合变分自编码器与因果图结构，生成符合因果关系的金融时间序列。
- 在模拟数据上反事实概率估计误差低至0.03-0.10（L1距离）。
- 适合做压力测试和场景分析，适用于金融风控与量化研究者。
基于深度生成模型的市场生成器在合成金融数据方面展现出潜力，但现有方法缺乏进行反事实分析与风险评估所必需的因果推理能力。本文提出时序神经因果模型变分自编码器（TNCM-VAE），将变分自编码器与结构因果模型相结合，生成既保留时间依赖性又符合因果关系的反事实金融时间序列。该方法通过解码器架构中的有向无环图施加因果约束，并采用因果Wasserstein距离进行训练。我们在受奥恩斯坦-乌伦贝克过程启发的自回归模型上验证了该方法，在反事实概率估计中表现出色，与真实值的L1距离低至0.03–0.10。模型可生成符合底层因果机制的合理反事实市场路径，支持金融压力测试、情景分析与增强型回测。
原文摘要 · Abstract (English)
Market generators using deep generative models have shown promise for synthetic financial data generation, but existing approaches lack causal reasoning capabilities essential for counterfactual analysis and risk assessment. We propose a Time-series Neural Causal Model VAE (TNCM-VAE) that combines variational autoencoders with structural causal models to generate counterfactual financial time series while preserving both temporal dependencies and causal relationships. Our approach enforces causal constraints through directed acyclic graphs in the decoder architecture and employs the causal Wasserstein distance for training. We validate our method on synthetic autoregressive models inspired by the Ornstein-Uhlenbeck process, demonstrating superior performance in counterfactual probability estimation with L1 distances as low as 0.03-0.10 compared to ground truth. The model enables financial stress testing, scenario analysis, and enhanced backtesting by generating plausible counterfactual market trajectories that respect underlying causal mechanisms.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。