You're currently viewing an old version of this dataset. To see the current version, click here.

COMPAS Dataset

The COMPAS recidivism dataset contains 6,167 samples, and the task is to predict the recidivism of an individual based on criminal history, with the binary protected attribute being race (white and non-white) and an additional nine features.

Data and Resources

Cite this as

Bahar Taskeesen, Jos´e Blanchet, Daniel Kuhn, Viet Anh Nguyen (2024). Dataset: COMPAS Dataset. https://doi.org/10.57702/1gqvsa10

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Defined In https://doi.org/10.48550/arXiv.1806.03281
Citation
  • https://doi.org/10.48550/arXiv.2306.09468
  • https://doi.org/10.48550/arXiv.2012.04800
  • https://doi.org/10.1609/aaai.v34i04.6002
  • https://doi.org/10.48550/arXiv.2106.09992
Author Bahar Taskeesen
More Authors
Jos´e Blanchet
Daniel Kuhn
Viet Anh Nguyen
Homepage https://www.propublica.org/datastore/dataset/compas-recidivism-risk-score-data-and-analysis