Model interpretability

Model interpretability — Making your model confesses: Shapley values

In a previous post, I explained what it means for a model to be fair and why checking model fairness is such a critical task. I am starting here a series of posts where I will share with you some ways you can achieve different levels of interpretability from your models and make them confess. Today I will introduce you to the topic and our first method: Shapley values.

Introduction:

Miller, Tim. 2017 “Explanation in Artificial Intelligence: Insights from the Social Sciences.” defines interpretability as “the degree to which a human can understand the cause of a decision in a model”. So it means it’s something that you achieve in some sort of “degree”. A model can be “more interpretable” or “less interpretable”. Keep that in your head.

The reason we want interpretability is that when achieved, we would have a way to check the following (Doshi-Velez and Kim 2017):

• Fairness: See my post “What does it mean for a model to be fair”
• Privacy: Ensuring that sensitive information cannot be disclosed by the model. e.g. being able to guess sensitive information but submitting specific examples to the model.
• Robustness: Changes in the input…