23 September 2025
In financial markets, it’s easy to be seduced by patterns. A portfolio manager spots a link between GDP growth and equity returns. A risk analyst sees volatility rising in tandem with energy prices. A quant discovers a promising correlation in historical data. But do these patterns reveal causation - or are they just coincidences?
In A Causality Primer for Investment Professionals, published by the CFA Institute Research Foundation, Marcos López de Prado and Vincent Zoonekynd tackle this critical blind spot. The authors offer investment practitioners a clear, accessible framework for understanding and applying causal inference in real-world financial contexts.
For decades, the industry has relied on statistical tools like regression models and machine learning algorithms to uncover relationships in data. But as the authors explain, “correlation is not causation” is more than a cliché. In an increasingly complex, data-rich world, failure to distinguish between the two can result in flawed investment theses, mispriced risk, and poorly constructed portfolios.
Causal inference provides a more rigorous approach - one that asks not only whether two variables are linked, but why, how, and under what conditions. Drawing on the groundbreaking work of Judea Pearl and others in the field of causal science, the primer introduces tools such as Directed Acyclic Graphs (DAGs), counterfactual analysis, and the “do-calculus,” which allow investment professionals to map relationships, isolate effects, and simulate interventions.
López de Prado is careful to position these tools as practical rather than purely theoretical. For instance, DAGs can help identify omitted variable bias or reverse causality in factor models. Causal methods can improve scenario analysis and policy forecasting, enhance explainability in AI and machine learning systems, and strengthen evidence-based decision making - a growing imperative for fiduciaries, regulators, and stakeholders.
The primer also dismantles the myth that causal reasoning is incompatible with data-driven methods. On the contrary, it shows that a fusion of domain expertise, thoughtful modeling, and causal inference can lead to more resilient and adaptive investment processes - especially in the face of regime changes, black swan events, or structural shifts.
Ultimately, A Causality Primer for Investment Professionals is more than a technical guide. It’s a call to action. As financial markets become more interconnected, volatile, and shaped by external forces - from geopolitics to climate policy to AI - investors must go beyond descriptive statistics and ask deeper, more meaningful questions.
“Causal reasoning,” the authors write, “is what distinguishes science from superstition.” In a world awash with data, the ability to understand why things happen - not just what happened - may prove to be the most valuable skill of all.