UpNext: Careers in Data Analytics for Liberal Arts - Interpretability and Fairness in AI

Daisy Zhuo ’12 (Mathematics), Co-Founding Partner at Interpretable AI will discuss the importance of interpretability and fairness of machine learning methods in real-world settings. The discussion will compare classical machine learning methods including regression, decision trees, ensemble models, and deep learning as well as explainability tools such as Lime and SHAP. Daisy will also introduce some cutting-edge research such as Optimal Decision Trees pioneered by her co-founders at MIT that bridges the gap between interpretability and performance. Finally, she will show interpretability in action with some real-world analytics cases that Interpretable AI has worked on in finance and medicine.