Data mining for discrimination discovery

By Salvatore Ruggieri, Dino Pedreschi, Franco Turini. 2010

251 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Law, Political Science and International Relations, AI Ethics, Fairness & Society

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Law

In Political Science and International Relations

In AI Ethics, Fairness & Society

Citations in the corpus

Causal Modeling-Based Discrimination Discovery and Removal: Criteria, Bounds, and Algorithms (2019, background): “Discrimination discovery and removal from historical data have received increasing attention over the past few years in data science [1], [2], [3], [4], [5].”
Fairness and Abstraction in Sociotechnical Systems (2019, background): “For example, the earliest fair-ML work by Ruggieri et al. formulates "fairness" as a goal for model optimization [59].”
A Causal Framework for Discovering and Removing Direct and Indirect Discrimination (2016, background): “Discrimination discovery and removal has received an increasing attention over the past few years in data science (Hajian and Domingo-Ferrer 2013; Kamiran and Calders 2012; Ruggieri, Pedreschi, and Turini 2010; Romei and Ruggieri 2014; Feldman et al. 2015).”
Achieving Non-Discrimination in Data Release (2016, methodology): “1 INTRODUCTION Discrimination discovery and prevention/removal has been an active research area recently [9, 12, 16, 28, 29, 39].”
A survey on measuring indirect discrimination in machine learning (2015, background): “…discovery typically mines association and classiﬁ-cation rules from the data, and then assesses those rules in terms of potential discrimination [Ruggieri et al. 2010; Romei et al. 2012; Hajian and Domingo-Ferrer 2013; Pedreschi et al. 2012; Luong et al. 2011; Mancuhan and Clifton 2014].”
Exposing the probabilistic causal structure of discrimination (2015, methodology): “However, following the approaches of [30,31], and [39], the contingency table shown in Fig.”
Using Loglinear Model for Discrimination Discovery and Prevention (2016, background): “Various business models have been built around the collection and use of individual data including the above protected attributes to make important decisions like employment, credit, and insurance.”
Meaningful Explanations of Black Box AI Decision Systems (2019, background): “…as demonstrated in the lively stream of research in discrimination-aware data mining, started by our research group in 2008 (Pedreschi, Ruggieri, and Turini 2008; Ruggieri, Pedreschi, and Turini 2010), but it is unlikely that rules in their simplest form will solve the general explanation problem.”
Discrimination- and privacy-aware patterns (2015, methodology): “Pedreschi et al. (2008, 2009a, b), Ruggieri et al. (2010) have introduced data mining approaches for discrimination discovery.”
Causal Discrimination Discovery Through Propensity Score Analysis (2016, methodology): “Earlier studies have primarily relied upon simple statistical analysis involving association or correlation measures [5, 15, 22, 23, 25] However, such analyses can produce misleading conclusions because they largely ignore the effect of confounding variables – variables that cam be used to determine”
Measuring discrimination in algorithmic decision making (2017, background): “A data mining approach for discrimination discovery typically extracts association and classification rules from data, and then evaluates those rules in terms of potential discrimination [28,39,40,47,49,53,54].”
A Roadmap for a Rigorous Science of Interpretability (2017, background): “…important criteria such as safety [Otte, 2013, Amodei et al., 2016, Varshney and Alemzadeh, 2016], nondiscrimination [Bostrom and Yudkowsky, 2014, Ruggieri et al., 2010, Hardt et al., 2016], avoiding technical debt [Sculley et al., 2015], or providing the right to explanation [Goodman and…”
Discrimination Prevention using Privacy Preserving Techniques (2015, background): “PD-classification rule is a classification rule which contains Potentially Discriminatory (PD) item set [2].”