With the help of machine learning, Swiss researchers have found that foreign jobseekers are on average 6.5% less likely to be contacted by recruiters than Swiss people with identical requirements.This content was published on January 21, 2021 - 16:48
Most studies on discrimination in recruitment have used methods such as sending fictitious CVs to recruiters. These are typically costly and analyse only specific job applicants.
However, a studyExternal link published this week in science journal Nature, led by researchers from federal technology institute ETH Zurich and the KOF Economic Research Center, tracked the search behaviour of recruiters on employment websites and used machine learning to control for all relevant jobseeker characteristics that are visible to recruiters.
The researchers worked with the State Secretariat for Economic Affairs (SECO) to gain access to anonymised data from Job-Room over a ten-month period. Job-Room is one of the largest recruitment platforms in Switzerland, containing profiles including gender, nationality, age and other factors of more than 150,000 job seekers.
“Our method allows us to study discrimination across different professions and points in time, and to analyse the entire search process on the platform,” said co-author Daniel Kopp from KOF. “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.”
The results revealed that the rates of contact by recruiters were 4-19% lower (on average 6.5% lower) for individuals from immigrant and minority ethnic groups, depending on their country of origin, than for citizens from the majority group. Discrimination was particularly pronounced for migrants from the Balkans, Africa, the Middle East and Asia.
The researchers also found that time of day mattered. Foreign origin has a stronger negative impact towards noon and in the evening – when recruiters review CVs faster.
“This result suggests that unconscious biases, such as stereotypes about minorities, also contribute to discrimination,” said co-author Dominik Hangartner. These unconscious biases might play a larger role when we are tired or want to leave work, the study noted.