arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2511.04469cs.LGphysics.data-anq-fin.CPstat.MEstat.OT
收藏

迈向因果市场模拟器

Towards Causal Market Simulators

National University of Singapore(新加坡国立大学);Veracruz Mexico(墨西哥韦拉克鲁斯)

Dennis Thumm, Luis Ontaneda Mijares

AI总结:

提出一种结合变分自编码器与结构因果模型的时间序列神经因果模型VAE(TNCM-VAE),用于生成保留时间依赖和因果关系的反事实金融时间序列,在合成数据上实现低至0.03-0.10的L1距离。

摘要:

使用深度生成模型的市场生成器在合成金融数据生成方面显示出前景,但现有方法缺乏反事实分析和风险评估所必需的因果推理能力。我们提出了一种时间序列神经因果模型VAE(TNCM-VAE),它将变分自编码器与结构因果模型相结合,以生成反事实金融时间序列,同时保留时间依赖性和因果关系。我们的方法通过解码器架构中的有向无环图施加因果约束,并使用因果Wasserstein距离进行训练。我们在受Ornstein-Uhlenbeck过程启发的合成自回归模型上验证了该方法,在反事实概率估计中表现出优越性能,与真实值相比L1距离低至0.03-0.10。该模型通过生成尊重潜在因果机制的合理反事实市场轨迹,实现了金融压力测试、情景分析和增强回测。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑