Introduction to Explainable Machine Learning Using Stata

Music City Center 

Room: CC-107B 

Machine learning (ML) has become a powerful tool for modeling complex data and providing accurate predictions. However, the "black-box" nature of many ML models raises concerns about explainability and trustworthiness. Explainable Machine Learning (XML) enhances transparency and understanding of machine learning predictions, addressing these challenges. This workshop aims to provide a practical guide to XML techniques. We will begin with an introduction to ensemble decision tree models, such as random forests and gradient boosting, which are widely used but often difficult to interpret. The focus will then shift to methods for explaining predictions using global and local XML techniques, including global surrogate models, variable importance, partial dependence plots, SHAP values, and individual conditional expectation (ICE) plots. Participants will gain hands-on experience through examples and case studies implemented in Stata's H2OML suite of commands. No prior knowledge of Stata is required, although a basic understanding of ML will be beneficial.

Stata