Explainable and Non-explainable Discrimination in Classification - Discrimination and Privacy in the Information Society - page 163

We argued that the techniques, that do not take into account the explainable part
of the discrimination, may tend to overshoot and thus introduce a reverse discrimi-
nation, which is undesirable as well. We explained how to measure discrimination
in data or decisions output by a classifier by explicitly considering explainable and
illegal discrimination.
Finally, we presented the local techniques that remove exactly the illegal dis-
crimination, allowing the differences in decisions to be present as long as they are
explainable. These techniques preprocess the training data in such a way that it no
longer contains illegal discrimination. After preprocessing classifiers that are trained
using this data are expected not to capture the illegal discrimination. Our com-
putational experiments demonstrated the effectiveness of the local preprocessing
techniques.
References
Ahearn, T.: Discrimination lawsuit shows importance of employer policy on the use of crim-
inal records during background checks (2010),
http://www.esrcheck.com/wordpress/2010/04/12/
Asuncion, A., Newman, D.: UCI machine learning repository (2007),
http://archive.ics.uci.edu/ml/
Bickel, P., Hammel, E., O'connell, J.: Sex bias in graduate admissions: Data from Berkeley.
Science 187(4175) (1975)
Calders, T., Kamiran, F., Pechenizkiy, M.: Building classifiers with independency constraints.
In: IEEE ICDM Workshop on Domain Driven Data Mining, pp. 13-18 (2009)
Calders, T., Verwer, S.: Three naive bayes approaches for discrimination-free classification.
Data Mining and Knowledge Discovery 21, 277-292 (2010)
Dutch Central Bureau for Statistics, 'Volkstelling' (2001),
http://easy.dans.knaw.nl/dms
Hart, M.: Subjective decisionmaking and unconscious discrimination. Alabama Law Re-
view 56, 741 (2005); University of Colorado, Law Legal Studies Research Paper 06-26
Kamiran, F., Calders, T.: Classification with no discrimination by preferential sampling.
In: Proceedings of the 19th Annual Machine Learning Conference of Belgium and The
Netherlands (BENELEARN 2010), pp. 1-6 (2010)
Kamiran, F., Calders, T., Pechenizkiy, M.: Discrimination aware decision tree learning. In:
Proceedings of IEEE ICDM International Conference on Data Mining (ICDM 2010), pp.
869-874 (2010)
Legislation: The us equal pay act (1963),
http://www.eeoc.gov/laws/statutes/epa.cfm
Pedreschi, D., Ruggieri, S., Turini, F.: Discrimination-aware data mining. In: Proceedings
of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data
Mining (KDD 2008), pp. 560-568 (2008)
Pedreschi, D., Ruggieri, S., Turini, F.: Measuring discrimination in socially-sensitive deci-
sion records. In: Proceedings of the SIAM International Conference on Data Mining SDM
2009, pp. 581-592 (2009)