shftan / auditblackbox

Data and code for the paper "Distill-and-Compare: Auditing Black-Box Models Using Transparent Model Distillation" presented at AAAI/ACM AIES 2018. https://arxiv.org/abs/1710.06169

auditblackbox

This GitHub repo has:

• code to clean publicly-available data sets with both risk scores and actual outcomes (COMPAS, Chicago Police, NYPD Stop-and-Frisk, Lending Club). This code is run-able.
• pseudocode for distillation setup proposed in the paper "Distill-and-Compare: Auditing Black-Box Models Using Transparent Model Distillation" presented at AAAI/ACM AIES 2018. https://arxiv.org/abs/1710.06169. You will need to pick a transparent model class and implement it / call an implementation of it.

Please email [e-mail] if you have questions.