Please note: The algorithm descriptions in English have been automatically translated. Errors may have been introduced in this process. For the original descriptions, go to the Dutch version of the Algorithm Register.

Job Agreement Candidate Screener (KVB)

Finds suitable candidates with a disability for employers
Last change on 22nd of July 2026, at 12:23 (CET) | Publication Standard 1.0
Publication category
Other algorithms
Impact assessment
N/A
Status
Out of use

General information

Theme

Social Security

Begin date

2017-01

End date

2026-07

Contact information

https://uwv.nl/nl/service-en-contact/contact-uwv

Responsible use

Goal and impact

The KVB was launched in 2017 under the Participation Act. This Act is designed to help more people find work. This includes people with a disability. With the KVB, employers can specify on werk.nl what sort of staff they are looking for. They create a search profile and can then see if there are any people with a disability who match their requirements.

Considerations

The KVB is a tool on werk.nl for employers and intermediaries, such as temporary employment agencies. It enables them to find suitable candidates who fall under the employment agreement. These are people who, due to a work-related disability, are unable to earn the minimum wage but are capable of performing specific types of work.

Human intervention

Our staff monitor the use of the algorithm in the following ways:

  • Employers decide which candidates from the list of (anonymous) candidates they would like to contact. They then submit a request to our Employer Service Point (WSP). A member of staff at the WSP then discusses with the employer the profile the candidate must meet, how many people the employer wishes to interview and the timeframe involved. An adviser at the WSP then matches the candidates with the employer or intermediary.
  • If the first 200 candidates do not prove suitable, our adviser can also suggest people who have not been shortlisted by the algorithm. 
  • Employers can also read the personal motivation or explanation that candidates can enter themselves in free-text fields. This information is not used by the algorithm, but helps employers and recruitment agencies to gain a better understanding of a candidate.

Risk management

We ensure that we (continue to) comply with information security and privacy requirements. We do this in the following ways: 

  • We are constantly working on maintaining the algorithm. 
  • We comply with the Records Act by deleting data that is no longer relevant.


Preventing discrimination in the algorithm
  • The algorithm does not use personal data such as name, address and age. 
  • The profiles of candidates displayed by the KVB are anonymous. 
  • Employers or recruitment agencies decide which profile to proceed with. The algorithm does not determine this.


Impact assessment

N/A

Operations

Data

The KVB uses the following profile data:

  • level of education
  • travel distance to the available vacancy
  • whether a candidate can travel independently
  • whether a candidate is available for work
  • how many hours a candidate can work per day 
  • how many hours a candidate can work per week 
  • what specific requirements a candidate has (for example, working alone, working with tools, or work involving a lot of walking and physical activity)
  • in which sector(s) a candidate wishes to work

Technical design

The employer can specify in the search criteria the requirements a candidate must meet. The KVB then checks to what extent candidates’ profiles match these criteria. Each answer is awarded a number of points. For example, if a candidate has ticked the same answers as the employer under ‘availability’ and ‘specific requirements’, this yields a high number of points. Ultimately, the algorithm displays a list of 200 potential candidates who fall within the scope of the job agreement. Profiles with the highest number of points appear at the top, whilst those with the lowest are at the bottom. The employer can then review the profiles and make their own selection.

Similar algorithm descriptions

  • Matchplaats (AI) supports the employment consultant in matching jobseekers with vacancies. The tool generates a list of potential matches between jobseekers and vacancies based on their skills, characteristics, interests and work-related points of interest. The work consultant discusses the potential matches deemed suitable with the jobseeker. If interested, the jobseeker is introduced to the employer.
    Last change on 13th of May 2026, at 7:05 (CET) | Publication Standard 1.0
    Publication category
    High-Risk AI-system
    Impact assessment
    DPIA, IAMA
    Status
    In use
  • A GBA is one part of the selection process. Candidates play several games to give an impression of the fit with the trainee profile. The test scores are visible in the candidate file as a report.
    Last change on 9th of October 2025, at 11:08 (CET) | Publication Standard 1.0
    Publication category
    Impactful algorithms
    Impact assessment
    IAMA, DPIA
    Status
    Out of use
  • Matching vacancy posted by employers and jobseekers.
    Last change on 19th of March 2024, at 10:33 (CET) | Publication Standard 1.0
    Publication category
    Other algorithms
    Impact assessment
    DPIA
    Status
    In use
  • CompetentNL is the Dutch standard for describing skills. CBS helps to keep CompetentNL up-to-date, independent and reliable. This is done by searching large-scale labour market data for skill descriptions; we call this skills detection. The results are shared with the organisation managing CompetentNL.
    Last change on 26th of March 2026, at 15:28 (CET) | Publication Standard 1.0
    Publication category
    Other algorithms
    Impact assessment
    DPIA
    Status
    In use
  • To support jobseekers in their orientation or job search, Gennep municipality offers citizens an online matching platform as a tool.
    Last change on 17th of December 2024, at 14:28 (CET) | Publication Standard 1.0
    Publication category
    Impactful algorithms
    Impact assessment
    Field not filled in.
    Status
    In development