Does Fair Ranking Improve Minority Outcomes? Understanding the Interplay of Human and Algorithmic Biases in Online Hiring

Ranking algorithms are being widely employed in various online hiring platforms including LinkedIn, TaskRabbit, and Fiverr. Prior research has demonstrated that ranking algorithms employed by these platforms are prone to a variety of undesirable biases, leading to the proposal of fair ranking algorithms (e.g., Det-Greedy) which increase exposure of underrepresented candidates. However, there is little to no work that explores whether fair ranking algorithms actually improve real world outcomes (e.g., hiring decisions) for underrepresented groups. Furthermore, there is no clear understanding as to how other factors (e.g., job context, inherent biases of the employers) may impact the efficacy of fair ranking in practice. In this work, we analyze various sources of gender biases in online hiring platforms, including the job context and inherent biases of employers and establish how these factors interact with ranking algorithms to affect hiring decisions. To the best of our knowledge, this work makes the first attempt at studying the interplay between the aforementioned factors in the context of online hiring. We carry out a large-scale user study simulating online hiring scenarios with data from TaskRabbit, a popular online freelancing site. Our results demonstrate that while fair ranking algorithms generally improve the selection rates of underrepresented minorities, their effectiveness relies heavily on the job contexts and candidate profiles.

[1]  Sean A. Munson,et al.  Unequal Representation and Gender Stereotypes in Image Search Results for Occupations , 2015, CHI.

[2]  Michael D. Ekstrand,et al.  Exploring author gender in book rating and recommendation , 2018, User Modeling and User-Adapted Interaction.

[3]  Sendhil Mullainathan,et al.  Are Emily and Greg More Employable Than Lakisha and Jamal , 2018 .

[4]  Ricardo Baeza-Yates,et al.  FA*IR: A Fair Top-k Ranking Algorithm , 2017, CIKM.

[5]  Mark T. Keane,et al.  Modeling Result-List Searching in the World Wide Web: The Role of Relevance Topologies and Trust Bias , 2006 .

[6]  B. Gutek,et al.  Sex Effects on Evaluation , 1980 .

[7]  Thorsten Joachims,et al.  Policy Learning for Fairness in Ranking , 2019, NeurIPS.

[8]  Thorsten Joachims,et al.  Accurately interpreting clickthrough data as implicit feedback , 2005, SIGIR '05.

[9]  Ben Green,et al.  Disparate Interactions: An Algorithm-in-the-Loop Analysis of Fairness in Risk Assessments , 2019, FAT.

[10]  Barry Smyth,et al.  Are people biased in their use of search engines? , 2008, CACM.

[11]  Andreas Krause,et al.  Mathematical Notions vs. Human Perception of Fairness: A Descriptive Approach to Fairness for Machine Learning , 2019, KDD.

[12]  Carlos Castillo,et al.  Exploring Artist Gender Bias in Music Recommendation , 2020, ComplexRec-ImpactRS@RecSys.

[13]  Johannes Wachs,et al.  Gender differences in participation and reward on Stack Overflow , 2018, Empirical Software Engineering.

[14]  M. de Rijke,et al.  Click Models for Web Search , 2015, Click Models for Web Search.

[15]  Shuguang Cui,et al.  Pairwise interaction analysis of logistic regression models , 2016, 2016 IEEE Global Conference on Signal and Information Processing (GlobalSIP).

[16]  Thorsten Joachims,et al.  Fairness of Exposure in Rankings , 2018, KDD.

[17]  Carlos Castillo,et al.  Reducing Disparate Exposure in Ranking: A Learning To Rank Approach , 2018, WWW.

[18]  Gary Marchionini,et al.  Synthesis Lectures on Information Concepts, Retrieval, and Services , 2009 .

[19]  Kori Inkpen Quinn,et al.  What You See Is What You Get? The Impact of Representation Criteria on Human Bias in Hiring , 2019, HCOMP.

[20]  Nisheeth K. Vishnoi,et al.  Interventions for ranking in the presence of implicit bias , 2020, FAT*.

[21]  Thorsten Joachims,et al.  Controlling Fairness and Bias in Dynamic Learning-to-Rank , 2020, SIGIR.

[22]  Sahin Cem Geyik,et al.  Fairness-Aware Ranking in Search & Recommendation Systems with Application to LinkedIn Talent Search , 2019, KDD.

[23]  Walter S. Lasecki,et al.  An Experimental Study of Bias in Platform Worker Ratings: The Role of Performance Quality and Gender , 2020, CHI.

[24]  Krishna P. Gummadi,et al.  Equity of Attention: Amortizing Individual Fairness in Rankings , 2018, SIGIR.

[25]  Loren G. Terveen,et al.  Avoiding the South Side and the Suburbs: The Geography of Mobile Crowdsourcing Markets , 2015, CSCW.

[26]  Toniann Pitassi,et al.  Fairness through awareness , 2011, ITCS '12.

[27]  David García,et al.  Bias in Online Freelance Marketplaces: Evidence from TaskRabbit and Fiverr , 2017, CSCW.