Fair AI Tools Action Set

The assessBias action calculates bias metrics for predictive models.

In predictive modeling, bias occurs when a model’s prediction or performance differs for different values of a given variable, referred to here as the "sensitive" variable. Prediction bias is measured by calculating the difference in average model prediction for different values of the sensitive variable, and performance bias is measured by calculating the difference in model performance for different values of the sensitive variable.

The assessBias action calculates performance statistics and average model predictions for each level of a nominal variable. The difference in these statistics is then calculated either by reporting the maximum pairwise difference among all levels or by comparing each level to a reference group in order to report a single number that represents model bias.