The most recent financial upheavals have cast doubt on the adequacy of some of the conventional quantitative risk management strategies, such as VaR (Value at Risk), in many common situations. Consequently, there has been an increasing need for verisimilar financial stress testings, namely simulating and analyzing financial portfolios in extreme, albeit rare scenarios. Unlike conventional risk management which exploits statistical correlations among financial instruments, here we focus our analysis on the notion of probabilistic causation, which is embodied by Suppes-Bayes Causal Networks (SBCNs); SBCNs are probabilistic graphical models that have many attractive features in terms of more accurate causal analysis for generating financial stress scenarios. In this paper, we present a novel approach for conducting stress testing of financial portfolios based on SBCNs in combination with classical machine learning classification tools. The resulting method is shown to be capable of correctly discovering the causal relationships among financial factors that affect the portfolios and thus, simulating stress testing scenarios with a higher accuracy and lower computational complexity than conventional Monte Carlo Simulations.
Predicting S&P500 Index direction with Transfer Learning and a Causal Graph as main Input
Université de Montreal（蒙特利尔大学）；Canada Mortgage and Housing Corporation（加拿大抵押贷款和住房公司）
我们提出了一个统一的多任务框架来表示金融市场动态的复杂和不确定的因果过程，然后预测任何类型的指数的运动与应用上的S & P 500指数的月度方向。我们的解决方案基于三个主要支柱：（i）使用迁移学习在所有金融市场之间共享知识和特征（表示、学习），增加训练样本的大小，并保持训练、验证和测试样本之间的稳定性。(ii)结合多学科知识（金融经济学、行为金融学、市场微观结构和投资组合构建理论），通过图形来表示任何金融市场的全球自上而下的动态。(iii)通过潜在变量/节点整合前瞻性非结构化数据，不同类型的上下文（长期，中期和短期），然后使用独特的VAE网络（参数共享）来同时学习它们的分布表示。在12年的测试期内，我们获得了74.3%，67%和0.42的准确性，F1得分和马修相关性，高于行业和其他基准，其中包括三个不稳定和难以预测的子期。
Predicting Liquidity-Aware Bond Yields using Causal GANs and Deep Reinforcement Learning with LLM Evaluation
School of Computer Science and Engineering, Vellore Institute of Technology, India（印度维杰雷理工学院计算机科学与工程学院）；Indian Institute of Science, Bangalore, India（印度班加罗尔印度科学学院）
