Research
By merging causality with machine learning, our goal is to achieve fundamental breakthroughs in developing AI systems that are aligned to society's values.
Working Papers
A Systems Thinking Approach to Algorithmic Fairness
We apply a sociotechnical approach to modeling the AI bias, fairness, and discrimination problem by merging concepts in machine learning, causal inference, and systems thinking to link AI systems to politics and the law.
Debiasing Alternative Data for Credit Underwriting Using Causal Inference
We apply causal inference to supervised machine learning to enable FinTechs to leverage alternative data for credit underwriting without causing proxy discrimination or digital redlining.