dp-100-data-scientist-assoc video for concept: Fairlearn is a Python package designed to analyze models and assess disparities in predictions and prediction
Concept: Fairlearn is a Python package designed to analyze models and assess disparities in predictions and prediction performance for sensitive features. Fairlearn integrates with Azure Machine Learning, allowing users to run experiments and upload dashboard metrics to their Azure ML workspace. The choice of parity constraint depends on the technique used and the specific fairness criteria being applied. Question: Which Fairlearn constraint matches the following description? " This constraint works with any mitigation algorithm to minimize disparities in the true positive rate across sensitive feature groups. In a binary classification scenario, it ensures that each group has a comparable ratio of true positive predictions."