Income tax selection module (selection module IH)

Dutch Tax and Customs Administration

This page contains information about the algorithm 'Selection module IH' for income tax/national insurance contributions returns. The algorithm assesses whether an income tax return can be accepted immediately or must be assessed manually, based on possible risks in the return.

Last change on 1st of May 2025, at 11:02 (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/selectiemodule-inkomensheffing-selectiemodule-ih/

Responsible use

Goal and impact

Every year, the Tax Administration receives more than 12 million income tax returns, which must be finalised with an assessment within 3 years. The Tax and Customs Administration uses an algorithm when assessing whether a return should be processed automatically or manually. To do so, the algorithm uses relevant data known to the Tax Administration. The selection module IH is an automated selection tool aimed at selecting returns for throw-out. All submitted returns go through the selection module IH.

The selection module contains a large number of selection rules that detect an uncertainty or potential compliance risk in the return. 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 both a positive correction and a negative correction (i.e. both a higher assessment and a lower assessment).

This short explainer video explains how the Inland Revenue checks the return.

• 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 judges 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 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 is used than necessary.

Anticipated risks include that a return may be wrongly automatically processed or wrongly ejected. These risks are mitigated by updating the selection rules annually, monitoring the operation of the algorithm, and training employees who review ejected returns. Measures are also taken to ensure that only necessary data is processed, in line with the AVG.

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. Health Insurance Act:
10. Double Tax Avoidance Decree 2001:
11. International (tax) treaties:

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/legalcontent/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/
• Zorgverzekeringswet: https://wetten.overheid.nl/BWBR0018450/
• Besluit voorkoming dubbele belasting 2001:: https://wetten.overheid.nl/BWBR0012095/
• Internationale (belasting)verdragen: : https://www.rijksoverheid.nl/documenten/circulaires/2023/03/09/verdragenop-het-gebied-van-directe-belastingen

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 Tax Authority regularly examines whether the data used is still necessary and can therefore be used.

Use of special personal data

The algorithm processes special personal data. The legal basis for processing special personal data is the Income Tax Act 2001 (Wet Inkomstenbelasting 2001). The scope for this basis stems from Article 9(2)(g) AVG. Special personal data are used and are necessary for carrying out the monitoring of the following schemes:

• Expenses for specific care costs (section 6.5 Wet IB 2001). There are conditions attached to the right to deduct specific care expenses. To test these conditions, special personal data are requested. It mainly concerns the amounts that are claimed to make use of the deduction.
• Weekend expenses for the disabled (section 6.6 Act IB 2001). There are conditions attached to the right to deduct the cost of short-term care for a severely disabled person. To test these conditions, special personal data are requested.
• Deductible gifts (section 6.9 IB Act 2001). To test the conditions for entitlement to gift deduction, the institution to which the gift is made is asked. This is necessary to determine whether the institution has ANBI status. Special personal data can be derived from the institution.
• Young Disabled Persons' Allowance (Wajong discount) (section 8.1 IB Act 2001). A condition for the young disabled person discount is the right to a Wajong benefit. Special personal data can be derived from the right to Wajong benefit.

Operations

Data

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

Links to data sources

• A-1 verklaringen : Sociale Verzekeringsbank (SVB)
• Aangiftegegevens Dividendbelasting: Belastingdienst
• Aangiftegegevens Inkomensheffing : Belastingdienst
• Aangiftegegevens Vennootschapsbelasting : Belastingdienst
• Bedrijfsgegevens : Kamer van Koophandel (KvK)
• Bankgegevens : Banken en verzekeraars
• Energie en Milieu Investeringsaftrek gegevens : Rijksdienst voor Ondernemend Nederland (RVO)
• Loon-, pensioen- en uitkeringsgegevens : Werkgevers, uitkeringsinstanties en pensioenuitvoerders
• Uitbetaald werk derden : Opdrachtgever of uitbetaler
• 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

Technical design

The algorithm consists of fixed selection rules drawn up by content experts based on laws, regulations and tax expertise. Each return is checked for signs of possible errors or compliance risks. If there are indications of these, the return is ejected for manual review by an employee. If no peculiarity is found, the return is automatically accepted. When ejected, the algorithm lists the issues an employee should pay attention to. The algorithm is not self-learning: it does not adjust itself based on previous outcomes. The rules are reviewed annually and adjusted where necessary.

External provider

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