AI Case Study

Albert Heijn, a Dutch grocer, reduced time to hire by 67% and improved candidate satisfaction by using machine learning to better match applicants to roles

The Dutch retailing corporation, Albert Heijn, used machine learning to improve candidate expectation management, increase satisfaction and establish a better fit between applicants and the traineeship they applied for.

Industry

Consumer Goods And Services

Retail General

Project Overview

“The goal was to automate our high volume selection process and decrease the amount of mismatches. To automate high volume selection process and decrease the amount of mismatches, a host accompanies candidates on a virtual journey through the office, tells something about the history of Albert Heijn and lets them feel the ‘overall vibe’. After that, she asks the candidate to fill in some information after which the journey continues. There’s a fine balance between showing and asking, it’s automated and manages expectations perfectly.” The data is then used to assess candidate's fit for the job.

Havert uses machine learning to assess the fit of candidates across dimensions like personality, culture, cognitive ability, language, skills etc. The algorithm uses history data to optimise hiring as well.

Reported Results

67% reduction in time to hire
87% applicant satisfaction rate

Technology

Function

Human Resources

Recruitment

Background

Albert Heijn is one of the largest European supermarket chains with 850 stores throughout The Netherlands, Belgium, Germany and Curacao.

Benefits

Data