Viewing fairness results for indirect bias

After you ensure that your model is set up for indirect bias analysis, you can view the results of the analysis.

Indirect bias occurs when one feature in a data set can be used to stand in for another. Watson OpenScale analyzes indirect bias when under specific conditions. For more details, see Configuring the Fairness monitor for indirect bias

The correlation strength is shown following the feature. The tooltip describes the proxy features.

The most relevant features are displayed. Expand each feature to see correlation strength values for the monitored groups and reference groups. For each group, the most-frequent values and the number of favorable outcomes for that class are displayed.