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.

Telephone Collection (Wahv)

If a person receives a second reminder for a traffic fine and does not pay it (in full), he or she can be called by the CJIB. The algorithm predicts for which person it is more likely that a personal conversation over the phone is the appropriate means of making a payment or reaching a payment appointment.

Last change on 10th of December 2024, at 14:00 (CET) | Publication Standard 1.0
Publication category
Impactful algorithms
Impact assessment
Field not filled in.
Status
In use

General information

Theme

  • Law
  • Traffic

Begin date

2021-06

Contact information

https://www.cjib.nl/forms/algoritme

Link to source registration

https://www.cjib.nl/telefonisch-innen

Responsible use

Goal and impact

One of the most important social tasks CJIB faces is socially responsible debt collection. CJIB wants to support people as much as possible in meeting their payment obligations and prevent an unnecessary increase in debt among citizens. CJIB has therefore invested in recent years in a personalised approach to debtors and making it possible to make payment arrangements for people who cannot pay (immediately). To this end, CJIB has developed additional services and possibilities.


The 'Telephone collection (Wahv)' algorithm supports one of these developed services. By proactively contacting people by phone who have outstanding claims (traffic offenders), CJIB can find out why they have not paid (in full). In this conversation, the CJIB employee can address any concerns about extra costs and tensions caused by the use of a bailiff by making an immediate payment, making a payment appointment or putting the person in contact with debt assistance.

Considerations

If a person receives a second reminder for a traffic fine and does not pay it (in full), the bailiff is then used. This step also follows from the law. The use of the bailiff involves, among other things, additional costs for the person. As stated, the goal of telephone debt collection is that the CJIB proactively calls those who do not (fully) pay the second demand for payment, in order to come to appropriate payment arrangements in a personal conversation and to prevent extra costs for citizens due to the use of the bailiff. CJIB cannot call everyone for this additional service. That is why an algorithm is deployed that predicts for which person a personal conversation over the phone is more likely to be the appropriate means for making a payment or arriving at a payment arrangement.


By proactively contacting people by phone who have outstanding claims (traffic offenders), CJIB can find out why they have not paid (in full). In this conversation, the CJIB employee can take away any concerns about extra costs and tensions caused by deploying a bailiff by making an immediate payment, making a payment appointment or putting the person in contact with debt assistance.


It also avoids additional social costs by deploying costly means of collection such as a bailiff.

Human intervention

The algorithm indicates which people with an outstanding traffic fine, CJIB should best call so that the use of the bailiff can be avoided. It is then up to the CJIB employee to decide who to call. For this, a person-oriented assessment takes place. This means, for example, that they look at whether there has been recent contact or whether an application for a payment arrangement has just been received.


So whether a citizen is called is ultimately up to the CJIB employee himself. In this way, CJIB ensures meaningful human intervention.

Risk management

CJIB is taking several measures to control and minimise the risks of the 'Telephone Collection (Wahv)' algorithm:

1. Transparency: CJIB publishes information about the algorithm in the algorithm register, so that citizens have insight into how the algorithm works and which decisions it supports. By using a decision tree, the algorithm is clear and transparent.

2. Human intervention: Although the algorithm predicts which individuals would benefit most from a telephone contact, the final decision and conversation remains in the hands of an employee. This ensures that there is always a human assessment.

3. Privacy protection: CJIB ensures that the data used by the algorithm is carefully managed and protected in accordance with applicable privacy laws.

4. Responsibility: The quality, fairness and security of the data and the algorithm are considered when collecting the data and creating the algorithm.

5. Monitoring and evaluation: CJIB continuously monitors the performance of the algorithm and regularly evaluates whether the algorithm produces the desired results without unintended negative effects.

6. Accountability and feedback: CJIB is open to feedback from citizens and other stakeholders to improve the algorithm and address any concerns.

Legal basis

The Administrative Enforcement of Traffic Regulations Act (also known as the Mulder Act or Wahv) regulates the administrative handling of common traffic offences in the Netherlands. Under this act, CJIB is in charge of collecting traffic offences.

Links to legal bases

Wet administratiefrechtelijke handhaving verkeersvoorschriften: https://wetten.overheid.nl/BWBR0004581/2024-03-01

Operations

Data

In developing and applying the algorithm, CJIB uses datasets. These datasets consist only of CJIB data on a person's traffic fines. They include the following data:

  • the outstanding amount;
  • the offence group to which the offence belongs;
  • the Wahv payment history.

Technical design

The algorithm predicts for which person it is more likely that a face-to-face conversation over the phone is the appropriate means of making a payment or arriving at a payment appointment. This is done with the help of a so-called decision tree. A decision tree works by asking questions that are answered with 'yes' or 'no'. This makes the algorithm easily explainable and transparent.

Similar algorithm descriptions

  • Someone with social assistance benefit and (also) income from employment or another benefit will receive less benefit under the Participation Act. Excess benefit payments can also be reclaimed. To get a good overview of this income, municipalities can request information from the IB.

    Last change on 17th of December 2024, at 12:26 (CET) | Publication Standard 1.0
    Publication category
    Impactful algorithms
    Impact assessment
    Field not filled in.
    Status
    In use
  • This algorithm is used within the BRP API Persons to provide the salutation of the requested person. The salutation is used as an introductory sentence in a letter or e-mail.

    Last change on 20th of October 2024, at 6:16 (CET) | Publication Standard 1.0
    Publication category
    Impactful algorithms
    Impact assessment
    DPIA
    Status
    In use
  • If someone receives social assistance benefits, other income must be offset against the benefits. This is because the assistance supplements income up to the assistance standard.

    Last change on 27th of November 2024, at 17:03 (CET) | Publication Standard 1.0
    Publication category
    Impactful algorithms
    Impact assessment
    Field not filled in.
    Status
    In development
  • The algorithm reveals whether a person who is in a penitentiary is receiving welfare benefits at the same time. If so, a signal is sent to the municipality.

    Last change on 5th of July 2024, at 8:38 (CET) | Publication Standard 1.0
    Publication category
    Impactful algorithms
    Impact assessment
    Field not filled in.
    Status
    In use
  • This algorithm supports BRP employees in preventing "look-alike fraud" by comparing the face of the person at the counter with the image in the scanned identity document.

    Last change on 14th of January 2025, at 10:43 (CET) | Publication Standard 1.0
    Publication category
    Impactful algorithms
    Impact assessment
    Field not filled in.
    Status
    In use