Measuring Discrimination in Socially-Sensitive Decision Records

By Dino Pedreschi, Salvatore Ruggieri, Franco Turini. 2009

258 citations recorded by the source corpus.

Subfields: Statistics and Probability, 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 Statistics and Probability

In AI Ethics, Fairness & Society

Citations in the corpus

Data preprocessing techniques for classification without discrimination (2011, background): “In Discrimination-Aware Data Mining two main directions can be distinguished: detection of discrimination [21–24], and the direction followed in this paper, namely learning classifiers if the data are discriminatory [4,15].”
Causal Modeling-Based Discrimination Discovery and Removal: Criteria, Bounds, and Algorithms (2019, background): “proposed to extract from the dataset classification rules which represent certain discrimination patterns [3], [13], [14].”
Achieving Non-Discrimination in Data Release (2016, methodology): “Classification rule-based methods [26, 27, 29] were proposed to represent certain discrimination patterns.”
Three naive Bayes approaches for discrimination-free classification (2010, background): “In [12, 11], concepts of undesired dependency due to discrimination were introduced.”
A survey on measuring indirect discrimination in machine learning (2015, methodology): “Impact ratio, also known as slift [Pedreschi et al. 2009], is the ratio of positive outcomes for the protected group over the general group, r = p ( y + | s 1 ) /p ( y + | s 0 ) . decisions This measure is used in the US courts for quantifying discrimination, the are deemed to be discriminatory if…”
Learning Fair Classifiers (2015, background): “The second strategy consists of modifying existing classifiers to limit discrimination (Cadlers & Verwer, 2010; Calders et al., 2013; Kamiran et al., 2012; Kamishima et al., 2011; 2013; Pedreschi et al., 2009).”
On the relation between accuracy and fairness in binary classification (2015, background): “A number of studies in discrimination-aware machine learning and data mining (Pedreschi et al., 2009; Kamiran et al., 2010; Calders & Verwer, 2010) focus on achieving equal acceptance rates (proportions of positive decisions) for favored and protected groups of individuals in binary classiﬁcation.”
Exposing the probabilistic causal structure of discrimination (2015, methodology): “Indirect discrimination discovery refers to the data mining task of discovering the attributes values that can act as a proxy to the protected groups and lead to discriminatory decisions indirectly [11,30,31].”
Preprocessing Technique for Discrimination Prevention in Data Mining (2014, methodology): “They had also implemented LP2DD [3] approach by integrating induction and deduction for finding evidence of discrimination of the overall reference model in 2009.”
Discrimination Aware Decision Tree Learning (2010, unknown): “Discrimination is a sociological term that refers to the unfair and unequal treatment of individuals of a certain group based solely on their afﬁliation to that particular group, category or class.”
Fairness-Aware Learning with Restriction of Universal Dependency using f-Divergences (2015, background): “We say f is discriminatory if the output of f is dependent on the viewpoint v [15].”
User-oriented Fairness in Recommendation (2021, background): “Group fairness requires that the protected groups should be treated similarly to the advantaged group or the populations as a whole [35].”
Anti-discrimination learning: a causal modeling-based framework (2017, background): “Pedreschi et al. proposed to extract from the dataset classiﬁcation rules which represent certain discrimination patterns [26,27,30].”
Discrimination-aware data mining: a survey (2017, methodology): “As described by Ruggieri et al. (2010a), the discrimination discovery process consists of finding all discriminatory classification rules depending on the laws and regulation of a specific country/region.”
A multidisciplinary survey on discrimination analysis (2013, methodology): “Statistical discrimination originated from Arrow (1971) and Phelps (1972), and was systematized by Aigner and Cain (1977); Coate and Loury (1993); Moro and Norman (2004).”