You’ve heard stories about a husband getting a much higher credit limit than his wife, a medical diagnostic test working better for some people than others, or certain people being approved for loans at a higher rate than others.
Unfairness can creep into our data in a variety of ways, and a machine learning model can often make the problem worse, not better!
We’ll start by discussing a high-level understanding of fairness in machine learning. Then we’ll cover methods for detecting whether or not unfairness is present and methods for correcting for unfairness, and open up the floor for discussion.
Fairness in machine learning is a critical topic to understand. Given the impact that data has on people’s lives, those of us using data to make decisions need to be aware of fairness!
Our talk will cover three things:
There are many ways to define unfairness, so we’ll agree on a definition and describe what it means.
We’ll learn techniques for detecting whether or not unfairness is present in our application.
If unfairness is present, how do we fix it? We’ll learn techniques for correcting for unfairness.
We will focus on applications in finance: think loans, income, credit scores. However, these techniques can be applied well beyond the realm of finance, so no background in finance is required! We’d love for you to bring your own applications for us to discuss.