Better decision support through exploratory discrimination-aware data mining: foundations and empirical evidence

By Bettina Berendt, Sören Preibusch. 2014

50 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Political Science and International Relations, Safety Research

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 Political Science and International Relations

In Safety Research

Citations in the corpus

European Union Regulations on Algorithmic Decision-Making and a "Right to Explanation" (2016, methodology): “Furthermore, a number of recent studies have attempted to tackle the issue of discrimination within algorithms by introducing tools to both identify [5, 29] and rectify [9, 16, 32, 6, 12, 14] cases of unwanted bias.”
'It's Reducing a Human Being to a Percentage': Perceptions of Justice in Algorithmic Decisions (2018, background): “Pr epr in t correct discrimination in data mining exist, these are aimed at data scientists implementing systems rather providing information to the individual decision-subjects affected by them [3, 59, 29, 23, 28].”
Measuring discrimination in algorithmic decision making (2017, background): “Interactions between human and algorithmic decision making is experimentally investigated in a recent study [6].”
The Tyranny of Data? The Bright and Dark Sides of Data-Driven Decision-Making for Social Good (2016, background): “For example, a number of studies have attempted to tackle the issue of discrimination within algorithms by introducing tools to both identify [6] and rectify [13, 6, 31] cases of unwanted bias.”
Fairness in Machine Learning: A Survey (2020, background): “References [114, 211] investigated visual mechanisms to better display “issues” with data to users, yet these approaches generally lack support for novice users [24].”
Fairer machine learning in the real world: Mitigating discrimination without collecting sensitive data (2017, methodology): “In some situations, sex might not be considered discriminatory where decisions hinge on differences in statistical life expectancies (Berendt and Preibusch, 2014).”
Discrimination- and privacy-aware patterns (2015, background): “…biases contained in the original data are removed so that no unfair decision models can be mined from the transformed data (Kamiran and Calders 2011; Hajian et al. 2011; Hajian and Domingo-Ferrer 2013; Loung et al. 2011; Dwork et al. 2012; Zemel et al. 2013; Berendt and Preibusch 2014).”