Income tax selection module (selection module IH) and risk tool supplements (RTA)

Dutch Tax and Customs Administration

This page contains information about the algorithm 'Selection module IH' for income tax/national insurance contributions (hereinafter income tax) returns and 'RTA' for income tax supplements.

Last change on 3rd of June 2025, at 9:32 (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/

Responsible use

Goal and impact

Every year, the Tax Administration receives millions of income tax returns and supplements. A supplement is when a citizen files an income tax return after a final assessment has already been imposed for the year in question. Hereafter, return also means supplement, unless otherwise stated. The Tax and Customs Administration must assess whether an assessment or other decision can be imposed in accordance with the return. The Tax and Customs Administration uses an algorithm when assessing whether a return should be processed automatically or manually. For this purpose, the algorithm uses relevant data known to the Tax and Customs Administration.The IH and RTA selection modules are automated selection tools with the purpose of selecting returns for ejection. All submitted returns go through the IH selection module and all submitted supplements through the RTA. The selection module and the RTA contain a large number of selection rules that detect an uncertainty or potential compliance risk. Based on the selection rules, the algorithm assesses whether the declaration can be accepted immediately. If not, the declaration is ejected and can be manually processed by an employee. For the ejected declarations, the algorithm lists the issues that require attention. The treatment can result in a correction either in favour or against the citizen.

This short explanation video explains how the Inland Revenue checks returns. The video is about returns, supplements are checked in the same way.

https://over-ons.belastingdienst.nl/organisatie/uitvoerings-handhavingsstrategie/hoe-controleert-de-belastingdienst-mijn-aangifte/

Considerations

For citizens, it is important that returns are processed quickly and carefully. The algorithm supports this interest and the Tax Administration employee.

The algorithm contributes to the systematic and accurate checking of returns. By deploying an algorithm, returns can be processed more efficiently, giving citizens clarity faster.

The algorithm determines the advice based on the relevant data. The alternative is that an employee would have to manually collect and assess the relevant data for all returns. This would make the process more error-prone and less efficient.

Human intervention

Human intervention in the Tax Administration context implies that a competent and knowledgeable employee plays a substantial role in decision-making.Human intervention is involved in the operation of the algorithm, but decisions are also made by the algorithm. The algorithm detects, selects and makes decisions. If, based on the selection rules, the algorithm assesses that the return can be accepted directly, an assessment follows automatically according to the data in the return. If the algorithm ejects a return for further assessment, the return can be processed by an employee. Human intervention by an employee occurs if the processing results in a deviation from the declaration.

Risk management

The Tax Administration is taking several measures to manage the risks of using the algorithm.

• 1. Transparency

The Tax and Customs Administration publishes information about the algorithm in the Tax and Customs Administration's algorithm register and the Central Government's algorithm register.

This allows citizens to understand the use and operation of the algorithm.

• Automated decision-making

The description of an algorithm explains this and also details the aspect of human intervention.

• 3. Privacy protection and legality

The Tax Authority ensures that the use of the data is assessed against the General Data Protection Regulation (GDPR).

The description of the algorithm also links to the applicable laws and regulations.

• 4. Responsibility

Using the Algorithm Register Policy Framework, the responsibilities and tasks in the use of algorithms are clearly described and safeguarded.

• Monitoring and evaluation

The operation of the algorithms is periodically tested. Based on this, selection rules can be adjusted.

Legal basis

1. General State Tax Act:
2. General Administrative Law Act:
3. General Data Protection Regulation:
4. General Data Protection Regulation Implementation Act:
5. Legal Restoration Act/ Box 3 Bridging Act
6. Income Tax Act 2001:
7. Citizen Service Number (General Provisions) Act:
8. Archives Act 1995:
9. International (tax) treaties
10. Health Insurance Act
11. Double taxation avoidance decree 2001

Links to legal bases

• Algemene wet inzake rijksbelastingen: : https://wetten.overheid.nl/BWBR0002320/
• Algemene wet bestuursrecht: : https://wetten.overheid.nl/BWBR0005537/
• Algemene verordening gegevensbescherming: : https://eur-lex.europa.eu/legal-content/NL/TXT/HTML/?uri=CELEX:32016R0679
• Uitvoeringswet algemene verordening gegevensbescherming: : https://wetten.overheid.nl/BWBR0040940/
• Wet rechtsherstel/ Overbruggingswet box 3: https://zoek.officielebekendmakingen.nl/stb-2022-534.html
• Wet Inkomstenbelasting 2001:: https://wetten.overheid.nl/BWBR0011353/
• Wet algemene bepalingen burgerservicenummer:: https://wetten.overheid.nl/BWBR0022428/
• Archiefwet 1995: : https://wetten.overheid.nl/BWBR0007376/
• Internationale (belasting) verdragen: https://www.rijksoverheid.nl/documenten/circulaires/2023/03/09/verdragen-op-het-gebied-van-directe-belastingen
• Zorgverzekeringswet: https://wetten.overheid.nl/BWBR0018450/2025-01-01
• Besluit voorkoming dubbele belasting 2001: https://wetten.overheid.nl/BWBR0012095/2020-01-01

Elaboration on impact assessments

The use of the data should be assessed against the AVG.

The AVG prescribes that no more data should be used than necessary. This is called data minimisation. The Inland Revenue regularly reviews whether the data used is still necessary and therefore may be used.

Operations

Data

1. A-1 statements
2. Dividend tax return details
3. Income tax return details
4. Corporate income tax return details
5. Bank details
6. Company details
7. Energy and environmental investment allowance data
8. Wage, pension and benefit data
9. Personal data
10. Transactions and income from rentals, sales or provision of personal services
11. Real estate data
12. Income insurance data
13. Third-party work paid out

Links to data sources

• A-1 verklaringen: Sociale Verzekeringsbank (SVB)
• Aangiftegegevens Dividendbelasting: Belastingdienst
• Aangiftegegevens Inkomensheffing: Belastingdienst
• Aangiftegegevens Vennootschapsbelasting: Belastingdienst
• Bankgegevens: Banken en verzekeraars
• Bedrijfsgegevens: Kamer van Koophandel (KvK)
• Energie en Milieu Investeringsaftrek gegevens: Rijksdienst voor Ondernemend Nederland (RVO)
• Loon-, pensioen- en uitkeringsgegevens: Werkgevers, uitkeringsinstanties en pensioenuitvoerders
• Persoonsgegevens: Basisregistratie Personen (BRP)
• Transacties en inkomsten uit verhuur, verkoop of leveren van persoonlijke diensten: Online platformen
• Vastgoedgegevens: Kadaster en Landelijke voorziening WOZ
• Inkomensverzekeringsgegevens: Verzekeraars
• Uitbetaald werk derden: Uitbetaler

Technical design

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

Based on the selection rules, the algorithm assesses whether the return can be accepted immediately. If not, the return is ejected and can be manually processed by an employee. For the ejected declarations, the algorithm lists the topics the clerk should pay attention to. Read more about this under the heading: 'Human intervention'.

The algorithm is not self-learning. This means that the algorithm does not develop itself while using it.