Detect Posttraining Data and Model Bias - Amazon SageMaker

Detect Posttraining Data and Model Bias

Posttraining bias analysis can help reveal biases that might have emanated from biases in the data, or from biases introduced by the classification and prediction algorithms. These analyses take into consideration the data, including the labels, and the predictions of a model. You assess performance by analyzing predicted labels or by comparing the predictions with the observed target values in the data with respect to groups with different attributes. There are different notions of fairness, each requiring different bias metrics to measure.

There are legal concepts of fairness that might not be easy to capture because they are hard to detect. For example, the US concept of disparate impact that occurs when a group, referred to as a less favored facet d, experiences an adverse effect even when the approach taken appears to be fair. This type of bias might not be due to a machine learning model, but might still be detectable by posttraining bias analysis.

Amazon SageMaker Clarify tries to ensure a consistent use of terminology. For a list of terms and their definitions, see Amazon SageMaker Clarify Terms for Bias and Fairness.

For additional information about posttraining bias metrics, see Fairness Measures for Machine Leaning in Finance.

Sample Notebooks

Amazon SageMaker Clarify provides the following sample notebook for posttraining bias detection:

This notebook has been verified to run in Amazon SageMaker Studio only. If you need instructions on how to open a notebook in Amazon SageMaker Studio, see Create or Open an Amazon SageMaker Studio Notebook. If you're prompted to choose a kernel, choose Python 3 (Data Science).