Discrimination-aware data mining
Dino Pedreschi, Salvatore Ruggieri, Franco Turini · ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD) · 2008
In the context of civil rights law, discrimination refers to unfair or unequal treatment of people based on membership to a category or a minority, without regard to individual merit. Rules extracted from databases by data mining techniques, such as classification or association rules, when used for decision tasks such as benefit or credit approval, can be discriminatory in the above sense. In this paper, the notion of discriminatory classification rules is introduced and studied. Providing a guarantee of non-discrimination is shown to be a non trivial task. A naive approach, like taking away all discriminatory attributes, is shown to be not enough when other background knowledge is available. Our approach leads to a precise formulation of the redlining problem along with a formal result relating discriminatory rules with apparently safe ones by means of background knowledge. An empirical assessment of the results on the German credit dataset is also provided.
Cited by 656 works. doi:10.1145/1401890.1401959
Authors
References
- UCI Repository of machine learning databases
- Fast Algorithms for Mining Association Rules in Large Databases
- The Economics of Discrimination.
- Privacy-preserving data mining
- Privacy-preserving data mining
- Integrating classification and association rule mining
- University of Chicago Press
- CPAR: Classification based on Predictive Association Rules
- Computational disclosure control: a primer on data privacy protection
- Selecting the right objective measure for association analysis