✳flâneur — a map of the web's best reading

Attack discrimination with smarter machine learning

research.google.com · 215 words · saved by 1 readers

This page is a companion to a recent paper by Hardt, Price, Srebro, which discusses ways to define and remove discrimination by improving machine learning systems. As machine learning is increasingly used to make important decisions across core social domains, the work of ensuring that these decisions aren't discriminatory becomes crucial. Here we discuss "threshold classifiers," a part of some machine learning systems that is critical to issues of discrimination. A threshold classifier essentially makes a yes/no decision, putting things in one category or another. We look at how these classifiers work, ways they can potentially be unfair, and how you might turn an unfair classifier into a fairer one. As an illustrative example, we focus on loan granting scenarios where a bank may grant or deny a loan based on a single, automatically computed number such as a credit score. In the diagram above, dark dots represent people who would pay off a loan, and the light dots those who wouldn't.

People + AI Research We are Designers People + AI Research (PAIR) is a multidisciplinary team at Google that explores the human side of AI by doing fundamental research, building tools, creating design frameworks, and working with diverse communities. We believe that for machine learning to achieve its positive potential, it needs to be participatory, involving the communities it affects and guided by a diverse set of citizens, policy-makers, activists, artists and more. Check out our work People + AI Guidebook A friendly, practical guide that lays out some best practices for creating

Explore this link on the map →

related reading