Scientists have leveraged big data from recruitment platforms and machine learning to study hiring discrimination. They find that discrimination against immigrants depends, among other things, on the time of day, and that both men and women face discrimination.
This type of discrimination violates the principle of equal opportunities. For those affected, this may have long-term disadvantages, such as longer unemployment or lower wages. That’s why it is crucial to understand who experiences discrimination and why.
Foreign origin has a stronger negative impact towards noon and in the evening—when recruiters review CVs faster.
The research team collaborated with the State Secretariat for Economic Affairs (SECO) to gain access to anonymized data from Job-Room, one of the largest recruitment platforms in Switzerland. Job-Room contains profiles of more than 150,000 job seekers.
Recruiters hiring on Job-Room specify the criteria required for a particular job. They then receive a list of suitable candidates and can view their profiles. Among other things, the profiles contain information on expertise, gender, nationality, and language skills of candidates. If recruiters are interested in particular candidates, they can contact them with just one click and invite them to a job interview.
Why study a job site?
Over 10 months, the researchers analyzed which candidates were contacted for an interview, and how recruiters made their selection. Their novel approach—which has significant advantages over conventional methods of studying discrimination—let them determine how the origin or gender of a candidate influenced the likelihood of being contacted.
Previous research has mainly used correspondence studies to shed light on discrimination. In these studies, researchers send HR managers fictitious CVs that are identical except for the characteristic of interest, e.g. the applicant’s ethnicity. The researchers then record which applicants are invited to an interview.
This is a costly and—because of its interference in actual hiring processes—not unproblematic procedure. Furthermore, correspondence studies are typically limited to few applications and occupations.
“By contrast, our method allows us to study discrimination across different professions and points in time, and to analyze the entire search process on the platform. We know which candidates are displayed to recruiters, when, and for how long recruiters view a profile, if they click on the contact button—and we observe millions of such decisions,” says coauthor Daniel Kopp of KOF Swiss Economic Institute.
Hiring discrimination and time of day
The research team finds that, on average, immigrant jobseekers were 6.5% less likely to be contacted than Swiss jobseekers with otherwise identical characteristics. This discrimination was particularly pronounced for migrants from the Balkans, Africa, the Middle East, and Asia, who often face prejudice in everyday life.
The researchers were able to show that a foreign origin has a stronger negative impact towards noon and in the evening—when recruiters review CVs faster—so the same recruiter makes different decisions depending on the time of day.
“This result suggests that unconscious biases, such as stereotypes about minorities, also contribute to discrimination,” says coauthor Dominik Hangartner of ETH Zurich’s Public Policy Group. These unconscious biases might play a larger role when we are tired or want to leave work.
Gender stereotypes
The study also finds that both men and women face discrimination. Given equal qualifications, women are mainly discriminated against in typical male professions, and men in typical female professions. In the five professions with the lowest proportion of women, women are 7% less likely to be contacted. In the five occupations with the highest proportion of women, they are 13% more likely to be contacted.
According to coauthor Michael Siegenthaler, some recruiters still seem to think that women are more suited to certain professions than men, and vice versa. “As a result, occupational segregation persists or is even increased.”
Online platforms such as Job-Room are becoming an increasingly important tool for recruitment. Does that mean discrimination in the job search is growing? The researchers do not expect this to be the case. There is no evidence of more discrimination on online platforms than in traditional recruitment processes. According to Kopp, discrimination is rather a structural and societal problem that is reflected across the entire labor market.
“But in the case of online portals, we can use the existing data to study hiring discrimination in detail and, based on the results, develop strategies to increase equal hiring opportunities.”
The study appears in Nature. Funding came from the Swiss National Science Foundation.
Source: Franzisca Kohler for ETH Zurich
