Ranks of Disparity: New approach fixes flaw in fairness algorithms
Short excerpt below. Click through to read at the original source.
As organizations increasingly rely on algorithms to rank candidates for jobs, university spots, and financial services, a new method, named hyperFA*IR, offers a more principled approach when picking candidates based on a limited pool of applicants, especially if minorities are few. The new interactive visualization, “Ranks of Disparity,” makes these complex dynamics visible.