fair-preprocessing / nips2017

Optimized Pre-Processing for Discrimination Prevention

This repository provides code for our optimization-based pre-processing framework for reducing discrimination introduced in our NIPS17 paper.

Dependencies

1. CVXPY
2. Jupyter

Using the code

1. Jupyter Notebook for pre-processing the Adult dataset can be found in the directory "Adult".
2. Jupyter Notebook for pre-processing the Compas dataset can be found in the directory "Compas".

Please cite the corresponding paper when using the code.

References

1. Optimized Pre-Processing for Discrimination Prevention
   Flavio Calmon, Dennis Wei, Bhanukiran Vinzamuri, Karthikeyan Natesan Ramamurthy and Kush R. Varshney.
   31st Advances in Neural Information Processing Systems (NIPS), Long Beach, CA, December 2017.