A careful exploration of the pitfalls of trying to extract causal insights from modern predictive machine learning models. — A joint article about causality and interpretable machine learning with Eleanor Dillon, Jacob LaRiviere, Jonathan Roth, and Vasilis Syrgkanis from Microsoft. Predictive machine learning models like XGBoost become even more powerful when paired with interpretability tools like SHAP. These tools identify the most informative relationships between the input features and…
