How to (partially) evaluate automated decision systems

Depicting the social impact of automated decision systems requires multiple interdisciplinary entry-points. In this paper we focus on the actual data and algorithms that produce specific outputs for the purposes of decision-making. The aim of this report is to outline the range of prominent methods that are used for auditing algorithms in data-driven systems and to also consider some of their limitations.

[1]  Patrick Ball,et al.  Big Data, Selection Bias, and the Statistical Patterns of Mortality in Conflict , 2014 .

[2]  B. Harcourt,et al.  Risk as a Proxy for Race , 2010 .

[3]  Suresh Venkatasubramanian,et al.  A comparative study of fairness-enhancing interventions in machine learning , 2018, FAT.

[4]  K. Lum,et al.  To predict and serve? , 2016 .

[5]  Zhe Zhang,et al.  Identifying Significant Predictive Bias in Classifiers , 2016, ArXiv.

[6]  Suresh Venkatasubramanian,et al.  Runaway Feedback Loops in Predictive Policing , 2017, FAT.

[7]  Indre Zliobaite,et al.  Measuring discrimination in algorithmic decision making , 2017, Data Mining and Knowledge Discovery.

[8]  Jieyu Zhao,et al.  Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints , 2017, EMNLP.

[9]  Henry Chai.  Fairness in machine learning lecture notes (Lecture 25) , 2019 .

[10]  Nathan Srebro,et al.  Equality of Opportunity in Supervised Learning , 2016, NIPS.

[11]  Carlos Eduardo Scheidegger,et al.  Certifying and Removing Disparate Impact , 2014, KDD.

[12]  Lalana Kagal,et al.  Iterative Orthogonal Feature Projection for Diagnosing Bias in Black-Box Models , 2016, ArXiv.

[13]  Andrew Gelman.  What’s the most important thing in statistics that’s not in the textbooks? , 2015 .

[14]  Franco Turini,et al.  k-NN as an implementation of situation testing for discrimination discovery and prevention , 2011, KDD.

[15]  Krishna P. Gummadi,et al.  From Parity to Preference-based Notions of Fairness in Classification , 2017, NIPS.

[16]  Thomas G. Dietterich.  What is machine learning? , 2020, Archives of Disease in Childhood.

[17]  Carlos Guestrin,et al.  "Why Should I Trust You?": Explaining the Predictions of Any Classifier , 2016, ArXiv.

[18]  Franco Turini,et al.  DCUBE: discrimination discovery in databases , 2010, SIGMOD Conference.

[19]  Krishna P. Gummadi,et al.  Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment , 2016, WWW.

[20]  Krishna P. Gummadi,et al.  Fairness Constraints: Mechanisms for Fair Classification , 2015, AISTATS.

[21]  Jennifer L. Skeem,et al.  Risk, Race, & Recidivism: Predictive Bias and Disparate Impact , 2016 .

[22]  Devin G. Pope,et al.  Implementing Anti-discrimination Policies in Statistical Profiling Models , 2011 .