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.

Accident risk

Ongevalrisico.nl makes road safety measurable by using risk profiles for o.b.v. road design, use and accidents. The risk profiles are built using road characteristics derived from open datasets and provincial datasets, such as road widths, verge obstacles and intensities

Last change on 9th of January 2025, at 9:36 (CET) | Publication Standard 1.0
Publication category
Other algorithms
Impact assessment
Field not filled in.
Status
In use

General information

Theme

Traffic

Begin date

2023-01

Contact information

algoritme@prvlimburg.nl

Link to publication website

https://www.limburg.nl/bestuur/open-overheid/algoritmeregister

Responsible use

Goal and impact

The algorithm is a tool to gain more, better and faster insights into traffic safety from a large number of different datasets. The results of the prediction model are used to advise traffic experts on (policy) choices that reduce the risk of traffic accidents. In addition, the model can be used in concrete projects to compare two or more designs in terms of road safety score. As such, the algorithm is only intended for internal use by (policy) employees of the Province.

Considerations

The advantage is that the prediction model clearly analyses the relevant road safety data (accident data and road characteristics). This allows identifying road safety risks, setting priorities or answering questions.


The disadvantage is that the results of the prediction model have to be interpreted properly by users. Not all existing road safety risks can be expressed in data/risk indicators, and data may contain errors.

Human intervention

The algorithm is an analytical tool. The outcomes are advisory and thus interpreted and verified by humans. Model outcomes are never adopted 1-to-1. So there is no automated decision-making.

Risk management

Data quality is checked periodically and updated annually. Risk profiles are also validated annually with actual accident data ensuring reliability. For explainability of risk predictions, values are displayed as transparently as possible. In addition, a disclaimer is present on the applications that outcomes are always an advice and can therefore deviate from the actual safety risks. The outcomes are always assessed by a traffic expert before use. No personal data are processed or shown.

Legal basis

The Road Traffic Act (section a4, c) and Road Infrastructure Safety Decree (section 3, et seq.).

Links to legal bases

  • Wegenverkeerswet 1994: https://wetten.overheid.nl/BWBR0006622/2024-06-19/#HoofdstukaIA_Artikela4c
  • Besluit Verkeersveiligheid Weginfrastructuur: https://wetten.overheid.nl/BWBR0048193/2023-06-01

Elaboration on impact assessments

No personal data and/or privacy-sensitive information will be used

Operations

Data

Among others, NWB, BGT, Openstreetmap, NDW V85 and OpenOV.

Links to data sources

ongevalrisico: https://ongevalrisico.nl/

Technical design

Structure of a risk:

- Risk: a (regional) road safety risk from, for example, CROW, SPV or defined by the road authority.

- Indicator: a measurable component of a risk. Each indicator consists of one or more variables that together yield an indicator score (a value between 0 - 1).

- Variable: a property derivable from data.


Calculation of risk profile: The final score of a road section is determined by making a weighted sum of all-risk scores. Like a risk score and an indcicator score, the risk profile is always a number between 0 and 1.

External provider

DOK data B.V.

Similar algorithm descriptions

  • Prediction model providing risk scores on road accidents based on a broad dataset of road characteristics and accidents.

    Last change on 23rd of August 2024, at 15:37 (CET) | Publication Standard 1.0
    Publication category
    Impactful algorithms
    Impact assessment
    Field not filled in.
    Status
    In development
  • The SVB conducts surveys focused on risk. This involves using algorithms to create risk profiles. If a citizen falls into a risk profile, they can be selected for a check by an employee of the Prevention & Enforcement Department.

    Last change on 29th of October 2024, at 8:06 (CET) | Publication Standard 1.0
    Publication category
    Impactful algorithms
    Impact assessment
    DPIA
    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
  • The risk prioritisation scores companies based on compliance behaviour, environmental variables and the latest controls. The higher a company is on the list, the earlier it is eligible for inspections which can have an impact on any occurrences on humans and the environment.

    Last change on 3rd of April 2024, at 13:50 (CET) | Publication Standard 1.0
    Publication category
    Other 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