Algorithm Overruns and Dropouts

Dutch Tax and Customs Administration

This page contains information about the algorithm 'Overstatements and Dropouts'. The algorithm supports Tax and Customs Administration staff in monitoring the correct recording of data by withholding agents in wage declarations. The Overschrijvers en Uitval algorithm helps Tax and Customs Administration staff to respond to potentially incorrect data in wage tax returns.

Last change on 30th of October 2025, at 15:43 (CET) | Publication Standard 1.0

• Publication category: Impactful algorithms
• Impact assessment: Field not filled in.
• Status: In use

General information

Theme

Public finance

Begin date

Field not filled in.

Contact information

[e-mail] .

Link to publication website

https://over-ons.belastingdienst.nl/onderwerpen/omgaan-met-gegevens/algoritmeregister/

Link to source registration

https://over-ons.belastingdienst.nl/onderwerpen/omgaan-met-gegevens/algoritmeregister/overschrijvers-en-uitval/

Responsible use

Goal and impact

The Tax Authority checks withholding agents for correct and complete declaration and payment of payroll taxes. Payroll taxes consist of wage tax, national insurance contributions, employee insurance and the income-related Healthcare Insurance Act contribution. Withholding agents (such as an employer, pension fund or benefits agency) deduct the wage tax and national insurance contributions from their employee's wages and, in some cases, the income-related Healthcare Insurance Act contribution. They remit this to the Tax Office. The employee insurance contributions and usually the income-dependent Healthcare Insurance Act contribution are not deducted from the employee's wage, but are paid by the employer to the Tax Administration.

The Tax and Customs Administration monitors the accuracy of employee data in the wage tax return. A withholding agent must periodically submit a wage tax return digitally to the Tax and Customs Administration.

If several wage tax returns are submitted for the same period for the same withholding agent, by another unknown withholding agent or tax service provider, an override may occur. The data in the various wage tax return messages may differ from each other to such an extent that one of the wage tax returns may not contain the correct current data. No substantive assessment on data in the wage declaration message takes place.

The Overwriters algorithm assists in detecting incorrectly stated data in a wage declaration message. This means that general data, such as naming, may differ in wage declaration messages. The consequences of incorrectly overwriting data may be that incorrect levy decisions are made by the Tax and Customs Administration and/or that the correct policy data are not registered with the UWV. This can affect the granting of benefits and allowances.

The Failure algorithm assists in detecting errors in the process. A handler assesses the error in the wage declaration, which could potentially lead to a rejection of the declaration.

A general description of how the wage declaration chain works is published on the "Wage declaration chain" site. (https://www.loonaangifteketen.nl/).

{see further under 'Considerations'}

Considerations

{following 'Purpose and impact'}

The Tax and Customs Administration periodically links back to withholding agents the discrepancies detected in the wage tax return notices. The withholding agent is requested to rectify the detected discrepancies in the return period. The aim of this process is correct administrative processing and assessment of data in the wage declaration notices.

Based on the clues from the algorithm, the handler can assess the return. It is the Tax Administration's handler who ultimately determines whether the wage return contains inaccuracies and can contact the withholding agent.

• Advantages of using algorithm

The monitoring of possible overwriting and drop-out of data is important for the withholding agent in order to prevent incorrect registration of data and thus achieve a correct wage return. We want to do this carefully. The algorithm can support a Tax Administration employee in this. As a result, the assessment is more careful, efficient and uniform.

Human intervention

Human intervention in the Tax Administration context implies that a competent and knowledgeable employee plays a substantial role in decision-making.

The operation of the algorithm always involves human intervention. The algorithm detects and selects. It is the Tax Administration employee who makes the decision whether to contact the withholding agent.

Risk management

The General Administrative Law Act (Awb) requires the government's actions to be transparent and lawful. The Tax Administration observes the general principles of good governance when applying and developing algorithms.

The algorithm uses data collected under various tax laws. As required by the AVG, no more data than necessary is used.

The selection rules are reviewed and adjusted if necessary to remain compliant with laws and regulations.

Legal basis

1. General State Tax Act:
2. General Administrative Law Act:
3. General Data Protection Regulation:
4. Payroll Tax Act 1964:
5. Social Insurance (Funding) Act:
6. General provisions Citizen Service Number Act:
7. Archives Act 1995:
8. Unemployment Act:
9. Sickness Act:
10. Work and Income according to Labour Capacity Act:
11. Disability Insurance Act:
12. Health Insurance Act:

Links to legal bases

• General State Tax Act:: https://wetten.overheid.nl/BWBR0002320/
• General Administrative Law Act:: https://wetten.overheid.nl/BWBR0005537/
• General Data Protection Regulation:: https://eur-lex.europa.eu/legal-content/NL/TXT/HTML/?uri=CELEX:32016R0679
• Payroll Tax Act 1964:: https://wetten.overheid.nl/BWBR0002471/
• Social Insurance Financing Act:: https://wetten.overheid.nl/BWBR0017745/
• General provisions Citizen Service Number Act:: https://wetten.overheid.nl/BWBR0022428/
• Archives Act 1995:: https://wetten.overheid.nl/BWBR0007376/
• Unemployment Act:: https://wetten.overheid.nl/BWBR0004045/
• Sickness law:: https://wetten.overheid.nl/BWBR0001888/
• Work and Income according to Labour Capacity Act:: https://wetten.overheid.nl/BWBR0019057/
• Disability Insurance Act:: https://wetten.overheid.nl/BWBR0002524/
• Health Insurance Act:: https://wetten.overheid.nl/BWBR0018450/

Elaboration on impact assessments

• Privacy and AVG

The use of data is tested against the General Data Protection Regulation (AVG). Reviewing personal data reveals any privacy risks and allows appropriate measures to be taken.

The AVG prescribes that no more data should be used than necessary. This is called data minimisation. The Tax Administration regularly examines whether the data used are still necessary and may therefore be used.

• Use of special personal data

The Overstatement and Dropout algorithm does not use special personal data.

• Equality and non-discrimination

The algorithm is assessed in line with applicable non-discrimination principles for direct and indirect discrimination. Processing as little personal data as possible reduces the risk of direct discrimination. Employees involved in developing and managing the algorithms receive training on data protection and bias.

Operations

Data

1. Identifying data (LH number)
2. Payroll tax return details

Links to data sources

• Identifying data (LH number): Belastingdienst
• Payroll tax return details: Belastingdienst

Technical design

The algorithm consists of selection rules created by content experts based on laws, regulations and expertise.

The algorithm is not self-learning. That means it does not evolve as it is used.

External provider

The algorithm was developed by Tax Administration staff and is also maintained internally.