What does it mean to 'solve' the problem of discrimination in hiring?: social, technical and legal perspectives from the UK on automated hiring systems

Discriminatory practices in recruitment and hiring are an ongoing issue that is a concern not just for workplace relations, but also for wider understandings of economic justice and inequality. The ability to get and keep a job is a key aspect of participating in society and sustaining livelihoods. Yet the way decisions are made on who is eligible for jobs, and why, are rapidly changing with the advent and growth in uptake of automated hiring systems (AHSs) powered by data-driven tools. Evidence of the extent of this uptake around the globe is scarce, but a recent report estimated that 98% of Fortune 500 companies use Applicant Tracking Systems of some kind in their hiring process, a trend driven by perceived efficiency measures and cost-savings. Key concerns about such AHSs include the lack of transparency and potential limitation of access to jobs for specific profiles. In relation to the latter, however, several of these AHSs claim to detect and mitigate discriminatory practices against protected groups and promote diversity and inclusion at work. Yet whilst these tools have a growing user-base around the world, such claims of 'bias mitigation' are rarely scrutinised and evaluated, and when done so, have almost exclusively been from a US socio-legal perspective. In this paper, we introduce a perspective outside the US by critically examining how three prominent automated hiring systems (AHSs) in regular use in the UK, HireVue, Pymetrics and Applied, understand and attempt to mitigate bias and discrimination. These systems have been chosen as they explicitly claim to address issues of discrimination in hiring and, unlike many of their competitors, provide some information about how their systems work that can inform an analysis. Using publicly available documents, we describe how their tools are designed, validated and audited for bias, highlighting assumptions and limitations, before situating these in the socio-legal context of the UK. The UK has a very different legal background to the US in terms not only of hiring and equality law, but also in terms of data protection (DP) law. We argue that this might be important for addressing concerns about transparency and could mean a challenge to building bias mitigation into AHSs definitively capable of meeting EU legal standards. This is significant as these AHSs, especially those developed in the US, may obscure rather than improve systemic discrimination in the workplace.

[1]  Ifeoma Ajunwa,et al.  Platforms at Work: Automated Hiring Platforms and Other New Intermediaries in the Organization of Work , 2018, Work and Labor in the Digital Age.

[2]  Seeta Peña Gangadharan,et al.  Decentering technology in discourse on discrimination* , 2019, Information, Communication & Society.

[3]  Michael Veale,et al.  Clarity, surprises, and further questions in the Article 29 Working Party draft guidance on automated decision-making and profiling , 2018, Comput. Law Secur. Rev..

[4]  Tony Doyle,et al.  Weapons of Math Destruction: How Big Data Increases Inequality and Threatens Democracy , 2017, Inf. Soc..

[5]  Kyla Thomas,et al.  The Labor Market Value of Taste: An Experimental Study of Class Bias in U.S. Employment , 2018 .

[6]  Malcolm Sargeant.  Discrimination and the Law (2nd Edition) , 2017 .

[7]  Teva J. Scheer.  Uniform Guidelines on Employee Selection Procedures , 2007 .

[8]  Michael Veale,et al.  Slave to the Algorithm? Why a 'Right to an Explanation' Is Probably Not the Remedy You Are Looking For , 2017 .

[9]  Andrew D. Selbst,et al.  Big Data's Disparate Impact , 2016 .

[10]  Carmela Troncoso,et al.  Questioning the assumptions behind fairness solutions , 2018, ArXiv.

[11]  M. I. V. Eale,et al.  SLAVE TO THE ALGORITHM ? WHY A ‘ RIGHT TO AN EXPLANATION ’ IS PROBABLY NOT THE REMEDY YOU ARE LOOKING FOR , 2017 .

[12]  Aaron C. Kay,et al.  Journal of Personality and Social Psychology Evidence That Gendered Wording in Job Advertisements Exists and Sustains Gender Inequality , 2011 .

[13]  Timnit Gebru,et al.  Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification , 2018, FAT.

[14]  폴리 프리다,et al.  Systems and methods for data-driven identification of talent , 2015 .

[15]  Christo Wilson,et al.  Investigating the Impact of Gender on Rank in Resume Search Engines , 2018, CHI.

[16]  Ifeoma Ajunwa,et al.  The Paradox of Automation as Anti-Bias Intervention , 2016 .

[17]  Solon Barocas,et al.  Mitigating Bias in Algorithmic Employment Screening: Evaluating Claims and Practices , 2019, SSRN Electronic Journal.

[18]  Luciano Floridi,et al.  Why a Right to Explanation of Automated Decision-Making Does Not Exist in the General Data Protection Regulation , 2017 .

[19]  Ifeoma Ajunwa,et al.  Limitless Worker Surveillance , 2016 .

[20]  Alexandra Chouldechova,et al.  Does mitigating ML's impact disparity require treatment disparity? , 2017, NeurIPS.

[21]  Julia Powles,et al.  "Meaningful Information" and the Right to Explanation , 2017, FAT.

[22]  Judy Wajcman,et al.  Automation: is it really different this time? , 2017, The British journal of sociology.

[23]  Aaron Rieke,et al.  Help wanted: an examination of hiring algorithms, equity, and bias , 2018 .

[24]  Seth Neel,et al.  Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness , 2017, ICML.

[25]  Daniele Senzani.  CHARTER OF FUNDAMENTAL RIGHTS OF THE EUROPEAN UNION , 2016 .

[26]  A. Hoffmann.  Where fairness fails: data, algorithms, and the limits of antidiscrimination discourse , 2019, Information, Communication & Society.

[27]  L. Macía,et al.  A Charter of Fundamental Rights for the European Union , 2000 .

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

[29]  Javier Sánchez-Monedero,et al.  The datafication of the workplace , 2019 .

[30]  Lina Dencik,et al.  A conceptual framework for approaching social justice in an age of datafication , 2018 .

[31]  D. Fitch,et al.  Review of "Algorithms of oppression: how search engines reinforce racism," by Noble, S. U. (2018). New York, New York: NYU Press. , 2018, CDQR.

[32]  Andrew Robinson,et al.  The quantified self: What counts in the neoliberal workplace , 2016, New Media Soc..

[33]  Deborah Hellman,et al.  Measuring Algorithmic Fairness , 2019 .

[34]  Danah Boyd,et al.  Fairness and Abstraction in Sociotechnical Systems , 2019, FAT.

[35]  Jacqueline Lane,et al.  Indirect discrimination, justification and proportionality: are UK claimants at a disadvantage? , 2017 .

[36]  Krishna P. Gummadi,et al.  Fairness Constraints: A Flexible Approach for Fair Classification , 2019, J. Mach. Learn. Res..

[37]  Julia Rubin,et al.  Fairness Definitions Explained , 2018, 2018 IEEE/ACM International Workshop on Software Fairness (FairWare).

[38]  Javier Sánchez-Monedero,et al.  How to (partially) evaluate automated decision systems , 2018 .

[39]  Ananth Balashankar,et al.  Pareto-Efficient Fairness for Skewed Subgroup Data , 2019 .

[40]  Sharad Goel,et al.  The Measure and Mismeasure of Fairness: A Critical Review of Fair Machine Learning , 2018, ArXiv.

[41]  Sach Mukherjee,et al.  Causal Learning via Manifold Regularization , 2016, J. Mach. Learn. Res..

[42]  Seth Flaxman,et al.  European Union Regulations on Algorithmic Decision-Making and a "Right to Explanation" , 2016, AI Mag..

[43]  Chris Russell,et al.  Counterfactual Explanations Without Opening the Black Box: Automated Decisions and the GDPR , 2017, ArXiv.