AI Explained Video series: What are Shapley Values?

We are starting a video series with quick, short snippets of information on Explainability and Explainable AI. The first in the series is one on Shapley values – axioms, challenges, and how it applies to explainability of ML models. Shapley values is an elegant attribution method from Cooperative Game Theory dating back to 1953. It … Continue reading “AI Explained Video series: What are Shapley Values?”

The State of Explainability: Impressions from Partnership on AI (PAI)’s Workshop in NYC

Two weeks ago, I had the opportunity to spend a day with 40 researchers, technologists, regulators, policy-makers, lawyers, and social scientists at PAI’s workshop on Explainability in ML.  PAI is a nonprofit that collaborates with over 100 organizations, across academic, governmental, industrial, and nonprofit sectors, to evaluate the social impact of artificial intelligence and to … Continue reading “The State of Explainability: Impressions from Partnership on AI (PAI)’s Workshop in NYC”

Counterfactual Explanations vs. Attribution based Explanations

This post is co-authored by Aalok Shanbhag and Ankur Taly As “black box” machine learning models spread to high stakes domains (e.g., lending, hiring, and healthcare), there is a growing need for explaining their predictions from end-user, regulatory, operations, and societal perspectives. Consequently, practical and scalable explainability approaches are being developed at a rapid pace.  … Continue reading “Counterfactual Explanations vs. Attribution based Explanations”

Identifying bias when sensitive attribute data is unavailable: Techniques for inferring protected characteristics

To evaluate whether decisions in lending, health care, hiring and beyond are made equitably across race or gender groups, organizations must know which individuals belong to each race and gender group. However, as we explored in our last post, the sensitive attribute data needed to conduct analyses of bias and fairness may not always be … Continue reading “Identifying bias when sensitive attribute data is unavailable: Techniques for inferring protected characteristics”

Identifying bias when sensitive attribute data is unavailable

The perils of automated decision-making systems are becoming increasingly apparent, with racial and gender bias documented in algorithmic hiring decisions, health care provision, and beyond. Decisions made by algorithmic systems may reflect issues with the historical data used to build them, and understanding discriminatory patterns in these systems can be a challenging task [1]. Moreover, … Continue reading “Identifying bias when sensitive attribute data is unavailable”