Fairness in Models
The discussion delves into the complexities of defining fairness in machine learning models, particularly in the context of mortgages and credit. Individual fairness focuses on ensuring similar individuals receive similar outcomes, while group fairness examines error rates across defined demographic groups. The conversation highlights the challenges of proxy correlations and the subjective nature of determining what constitutes a fair model, emphasizing the ongoing debate and need for clarity in defining fairness.In this clip
From this podcast
Gradient Dissent - A Machine Learning Podcast
Kathryn Hume — Financial Models, ML, and 17th-Century Philosophy
Related Questions