This repository contains the code for reproducing the simulations in our paper
Interventions for Ranking in the Presence of Implicit Bias
L. Elisa Celis, Anay Mehrotra, Nisheeth K. Vishnoi
ACM Conference on Fairness, Accountability, and Transparency, ACM FAT* 2020
arXiv: https://arxiv.org/abs/2011.04219
To run the simulations, inside the experiments
folder, execute
python experiments.py
To generate other additional plots in the paper, inside the experiments
folder, execute
python jee2009-additional-figs.py
python semantic-scholar-additional-figs.py
This repository also provides a copy of the 2009 IIT-JEE Scores Dataset released in response to a Right to Information application filed in June 2009 [1]. We use this dataset in our empirical evaluations.
from meza import io
record = io.read('jee2009.mdb')
result=[]
for i in range(384977):
result.append(next(record))
[1] RTI Complaint. Decision No. CIC/SG/C/2009/001088/5392, Complaint No. CIC/SG/C/2009/001088 Rajeev Kumar, 2009