Explainable and Non-explainable Discrimination in Classification - Discrimination and Privacy in the Information Society - page 149

Chapter 8
Explainable and Non-explainable
Discrimination in Classification

Faisal Kamiran and Indre Zliobaite

Abstract. Nowadays more and more decisions in lending, recruitment, grant or
study applications are partially being automated based on computational models
(classifiers) premised on historical data. If the historical data was discriminating to-
wards socially and legally protected groups, a model learnt over this data will make
discriminatory decisions in the future. As a solution, most of the discrimination-
free modeling techniques force the treatment of the sensitive groups to be equal
and do not take into account that some differences may be explained by other fac-
tors and thus justified. For example, disproportional recruitment rates for males and
females may be explainable by the fact that more males have higher education; treat-
ing males and females equally will introduce reverse discrimination, which may be
undesirable as well. Given that the law or domain experts specify which factors are
discriminatory (e.g. gender, marital status) and which can be used for explanation
(e.g. education), this chapter presents a methodology how to quantify the tolerable
difference in treatment of the sensitive groups. We instruct how to measure, which
part of the difference is explainable and present the local learning techniques that
remove exactly the illegal discrimination, allowing the differences in decisions to be
present as long as they are explainable.

8.1 Introduction

Data mining builds computational models from historical data. Classification is a
data mining task, where the goal is to learn the relation between given variables
in order to apply the learnt model in the future for decision making. Suppose an