Structural Causal Models

Structural Causal Models combine graphical representations with mathematical equations to describe the causal mechanisms of a system. In the context of financial derivatives, these models define how each variable, such as implied volatility or delta, is generated by its causal parents.

This approach allows for a complete description of the data-generating process, enabling analysts to perform complex interventions and counterfactual reasoning. Unlike standard regression, which only looks at associations, these models explicitly account for the underlying physics of the market.

They are particularly valuable for simulating the impact of protocol changes on system risk and contagion. By encoding domain knowledge into the model, researchers can create simulations that are more accurate and reliable than purely data-driven approaches.

These models provide a rigorous foundation for decision-making in high-stakes environments like decentralized finance. They help in identifying the root causes of market anomalies and designing more resilient economic systems.

This framework is essential for moving beyond simple correlations toward a true understanding of market mechanics.