Open Conference Systems, 50th Scientific meeting of the Italian Statistical Society

Font Size: 
Discrimination in machine learning algorithms
Roberta Pappadà, Francesco Pauli

Last modified: 2018-06-04


Machine learning algorithms are routinely used for business decisions which may directly affect individuals: for example because a credit scoring algorithms refuses them a loan. It is then relevant from an ethical (and legal) point of view to ensure that these algorithm do not discriminate based on sensitive attributes (sex, race), which may occur unwittingly and unknowingly by the operator and the management. Statistical tools and methods are then required to detect and eliminate such potential biases.

Full Text: PDF