This repository contains a software implementation of the methods described in:

Fairness without Harm: Decoupled Classifiers with Preference Guarantees
Berk Ustun, Yang Liu, David Parkes
International Conference on Machine Learning (ICML), 2019

• Python 3
• CPLEX

CPLEX is cross-platform commercial optimization tool with a Python API. It is free for students and faculty at accredited institutions. To get CPLEX:

1. Register for IBM OnTheHub
2. Download the IBM ILOG CPLEX Optimization Studio from the software catalog
3. Install the CPLEX Optimization Studio.
4. Setup the CPLEX Python API as described here.

If you have problems installing CPLEX, check the CPLEX user manual or the CPLEX forums.

The code in this repository is currently under active development, and may therefore change substantially with each commit.

If you end up using our code, please cite the following paper:

@InProceedings{pmlr-v97-ustun19a,
  title = 	 {Fairness without Harm: Decoupled Classifiers with Preference Guarantees},
  author = 	 {Ustun, Berk and Liu, Yang and Parkes, David},
  booktitle = 	 {Proceedings of the 36th International Conference on Machine Learning},
  pages = 	 {6373--6382},
  year = 	 {2019},
  editor = 	 {Chaudhuri, Kamalika and Salakhutdinov, Ruslan},
  volume = 	 {97},
  series = 	 {Proceedings of Machine Learning Research},
  address = 	 {Long Beach, California, USA},
  month = 	 {09--15 Jun},
  publisher = 	 {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v97/ustun19a/ustun19a.pdf},
  url = 	 {http://proceedings.mlr.press/v97/ustun19a.html},
}