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.
Risk model sales decline NOW
- Publication category
- Impactful algorithms
- Impact assessment
- Field not filled in.
- Status
- In use
General information
Theme
Begin date
Contact information
Responsible use
Goal and impact
The purpose of this algorithm (the risk model) is to support the Ministry of SZW in choosing which NOW applications should be further investigated for the accuracy of the declared turnover loss.
The risk model compares information provided by the applicant in the NOW application with information from public sources and with information from other government organisations. A very large number of NOW applications have been submitted. By using the risk model, choices can be made faster. As a result, employers receive a decision as soon as possible.
The impact for the vast majority of applicants is that they quickly receive a decision on their NOW application without the need for further investigation. For those applicants who do get selected, this means that partly with the help of the risk model, the stated loss of turnover will be investigated further. If a NOW application is investigated then it takes longer to make a decision than if a NOW application is not investigated.
Ultimately, the investigation may reveal a different turnover loss percentage than the applicant submitted in the NOW application. As a result, the final grant amount may differ from the grant amount the applicant expected based on the NOW application.
Considerations
Advantages:
Scale; Almost half a million applications have been submitted, spread over eight different rounds. If the ministry were to check all these NOW applications, it takes a lot of time and a lot of money. By selecting NOW applications for scrutiny using the risk model, we keep costs as low as possible for everyone: for employers, but also for the government.
Efficient working method; With the deployment of the algorithm (risk model), the working method is efficiently designed. The risk model helps staff make effective and accurate choices based on objective information. As a result, the vast majority of applicants quickly receive a decision without the need for further investigation. In this way, large numbers of applications can be quickly fed back to UWV.
Standardised working method; the Ministry of SZW uses information from other public sources for the risk model. This is information from, for example, the Chamber of Commerce on the start of the business and who owns it. This objective information is used in the risk model. With this, the risk model helps staff make choices based on objective information and comparisons.
Disadvantages
The risk model gives an indication of whether the stated turnover loss from a NOW application is correct. This indication is based on information from public sources and information from other government organisations. The model cannot take into account every unique situation that may apply to an employer. As a result, it does not always accurately reflect reality. Staff take this into account and therefore review NOW applications designated by the model at the individual level.
On the one hand, it happens that NOW applications are selected but the review does not reveal any inaccuracies. For these applicants, there is a longer processing time and an additional administrative burden. This is because the applicant has to prove that the information given in the NOW application is correct using data from records. On the other hand, not all possible risks are included in the risk model. This may result in incorrect NOW applications not being examined.
Human intervention
The risk model supports staff in the selection process so that they can make informed and efficient choices. The advice from the risk model is not necessarily decisive and the final selections are always based on human intervention by staff based on the four-eye principle. The selection process and the selected files are monitored by multi-level checks. The risk model has been evaluated several times in recent years and adjusted where necessary.
Risk management
The risk model has been reviewed and adjusted several times in recent years based on newly gained insights from the results of completed studies or on new objective information from other government organisations.
Legal basis
Temporary emergency measure bridging for job retention (first, second, third, fourth, fifth, sixth)
Operations
Data
Stated information from NOW applications, information from other government sources (including the Tax Office, Central Bureau of Statistics and the Chamber of Commerce) and information from NOW applications from other NOW tranches (if an employer submitted more than one NOW application).
Technical design
The risk model uses insights from historical data and predictions/estimates of a situation. In doing so, it uses functions that connect, rank, categorise and add relevant information. The risk model supports and advises through analyses and comparisons of, on the one hand, specified information in NOW applications and, on the other hand, information from public sources and data from government agencies. It supports and advises staff in the NOW application selection process to check the accuracy of the NOW application.
External provider
Similar algorithm descriptions
- The algorithm is used to make an automated risk assessment for all Applications for Fixed Chargesgemoetkoming, prior to automated or manual granting and payment of the advance.Last change on 30th of May 2024, at 12:57 (CET) | Publication Standard 1.0
- Publication category
- High-Risk AI-system
- Impact assessment
- Field not filled in.
- Status
- In use
Detecting risks in customs declarations for compliance with authorisation requirement of chemicals
Customs
This algorithm helps Customs to select goods for control based on risk. It uses declaration data from companies and considers whether or not there are increased risks of importing and exporting chemicals intended for use as drug precursors.Last change on 17th of December 2024, at 10:55 (CET) | Publication Standard 1.0- Publication category
- Impactful algorithms
- Impact assessment
- Field not filled in.
- Status
- In use
- This algorithm creates a risk sorting of educational institutions (schools, courses or school boards) to conduct targeted desk research, as part of the annual performance and risk analysis.Last change on 22nd of May 2024, at 8:41 (CET) | Publication Standard 1.0
- Publication category
- Impactful algorithms
- Impact assessment
- Field not filled in.
- Status
- In use
- This algorithm helps Customs to select goods for inspection based on risk. It uses declaration data from companies and considers whether or not there are risks of inaccuracies in the declarations.Last change on 28th of February 2024, at 12:29 (CET) | Publication Standard 1.0
- Publication category
- Impactful algorithms
- Impact assessment
- Field not filled in.
- Status
- In use
Detecting tax risks in customs declarations regarding the levying and collection of sales tax
Customs
This algorithm helps Customs to select goods for inspection based on risk. It uses declaration data from companies and considers whether or not there are risks of inaccuracies in the declarations for the purpose of determining correct financial measures and levies (including import duties and VAT).Last change on 10th of December 2024, at 7:53 (CET) | Publication Standard 1.0- Publication category
- Impactful algorithms
- Impact assessment
- Field not filled in.
- Status
- In use