Explaining black-box models using attribute importance, PDPs, and LIME
Domino Data Lab
AUGUST 1, 2021
PDPs for the bicycle count prediction model (Molnar, 2009). The surrogate model is often a simple linear model or a decision tree, which are innately interpretable, so the data collected from the perturbations and the corresponding class output can provide a good indication on what influences the model’s decision.
Let's personalize your content