A multidisciplinary survey on discrimination analysis

Romei, Andrea and Ruggieri, Salvatore (2011) A multidisciplinary survey on discrimination analysis. Technical Report del Dipartimento di Informatica . Università di Pisa, Pisa, IT.

Other (GZip) Available under License Creative Commons Attribution No Derivatives. Download (527Kb)

Abstract

Most of the decisions in the today's knowledge society are taken<br />on the basis of historical data by extracting models, patterns,<br />profiles, and rules of human behavior in support of (automated)<br />decision making. There is then the need of developing models,<br />methods and technologies for modelling the processes of<br />discrimination analysis in order to discover and prevent<br />discrimination phenomena. In this respect, discrimination analysis<br />from data should build over the large body of existing legal and<br />economic studies. This paper intends to provide a<br />multi-disciplinary survey of the literature on discrimination data<br />analysis, including methods for data collection, empirical<br />studies, controlled experiments, statistical evidence, and their<br />legal requirements and grounds. We cover the following mainstream<br />research lines: labour economic models, (quasi-)experimental<br />approaches such as auditing and controlled experiments,<br />profiling-based approaches such as racial profiling and credit<br />markets, and the recently blooming research on knowledge discovery<br />approaches.

Repository staff only actions