Start-up Entrepreneurs (STS)

Dutch Tax and Customs Administration

This algorithm helps Tax Administration staff in the timely detection of potentially incorrect and/or incomplete returns to improve supervision of the group of start-up entrepreneurs.

Last change on 19th of December 2025, at 12:30 (CET) | Publication Standard 1.0

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

General information

Theme

Public finance

Begin date

9-2025

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/startende-ondernemingen-sts/

Responsible use

Goal and impact

The number of start-ups is increasing every year. In the period from 2018 to 2023, this group grew on average 20% per year to about 97,000 entrepreneurs started in 2023. At the same time, we see the same 'beginner's mistakes' often being made in this group. The Enforcement Letter 2018 revealed that the subject group of start-up entrepreneurs is overrepresented in declaration and payment defaults.

This gives rise to the need for a structural solution for the timely detection of potentially incorrect and/or incomplete returns. With this, the start-up entrepreneur can be contacted earlier for the improvement of compliant behaviour, such as timely filing of returns and providing the right information on business operations. The earlier that behaviour can be improved, the better it is for entrepreneurs and the Tax Administration.

The algorithm puts snapshots of the data of start-up entrepreneurs in an order based on the start/duration of the business. This sequence is used only in the process described. Outside of that, they are not used, to avoid profiling that is not allowed.

Considerations

The Inland Revenue gives a lot of attention to proper supervision of start-ups with proactive and preventive measures. However, working preventively can never prevent errors and omissions in all cases; supervision therefore remains necessary.

This can be done by targeted checking of returns using the signals and treatment recommendations generated by this algorithm. In this way, the limited monitoring capacity can be used as effectively as possible.

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 always involved in the operation of the algorithm. The algorithm detects discrepancies and gives a point score through its decision rules. From this, it recommends a treatment proposal. It is the Tax Administration employee who makes the decision to adopt the treatment proposal and perform a tax substantive assessment.

Risk management

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

Conditions, a quality framework, have been drawn up by the Tax and Customs Administration for the development of algorithms. This contains rules and agreements that are followed during algorithm development. The conditions of the National Audit Authority are leading in this respect. At set moments, the Tax and Customs Administration checks whether the algorithm still meets the quality requirements.

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

The algorithm and selection rules are evaluated annually. If necessary, the selection rules are adjusted in cooperation with the tax inspector to remain compliant with laws and regulations.

The evaluation is carried out annually by the service unit that carries out the supervision, Belastingdienst-MKB, in cooperation with the service unit that developed the signalling model, Corporate Service Data Foundations and Analytics.

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. Payroll Tax Act 1964:
6. Income Tax Act 2001:
7. Corporation Tax Act 1969:
8. Turnover Tax Act 1968:
9. General Provisions Citizens' Service Number Act:
10. Archives Act 1995:

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
• General Data Protection Regulation Implementation Act:: https://wetten.overheid.nl/BWBR0040940/
• Payroll Tax Act 1964:: https://wetten.overheid.nl/BWBR0002471/
• Income Tax Act 2001:: https://wetten.overheid.nl/BWBR0011353/
• Corporation Tax Act 1969:: https://wetten.overheid.nl/BWBR0002672/
• Turnover Tax Act 1968:: https://wetten.overheid.nl/BWBR0002629/
• General provisions Citizen Service Number Act:: https://wetten.overheid.nl/BWBR0022428/
• Archives Act 1995:: https://wetten.overheid.nl/BWBR0007376/

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

Special personal data in the AVG include race, political views and religion.

The 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. Personal data (addresses and relations between natural persons, tax liability)
2. Business data (addresses and relationships, tax liability, tax number)
3. Financial products
4. Income tax return details (IH)
5. Corporation tax return details (VPB)
6. Turnover tax (OB) declaration details

Links to data sources

• Personal data (addresses and relations between natural persons, tax liability): Basisregistratie Personen (BRP)
• Company data (addresses and relations, tax liability, tax number): Kamer van Koophandel
• Financial products: Banken
• Income tax (IH) declaration details: Belastingdienst
• Corporate income tax (VPB) return details: Belastingdienst
• Turnover tax (OB) declaration details: Belastingdienst

Technical design

The algorithm consists of decision rules drawn up by content experts from the Tax Administration based on laws, regulations and expertise. Which decision rules are applied differs per group: the group of entrepreneurs whose tax liability started 9 to 12 months before the reference date and the group of entrepreneurs whose tax liability started 30 to 33 months before the reference date. This involves looking at data from multiple tax resources at the same time if possible, e.g. sales tax and income tax.

Based on the decision rules, the algorithm gives each start-up a score. For each group, signals from the businesses with the highest scores are picked up by Tax Administration staff. The staff assess the filing behaviour of these businesses for the need for further investigation and proceeding to follow-up actions, such as asking the taxpayer questions or imposing an assessment. Due to strategic importance in supervision, the decision rules cannot be made public.

The algorithm is not self-learning. This means that it does not evolve during its use.

External provider

The algorithm was developed by staff at the Inland Revenue and is also maintained internally.