Direct naar content

You are here:

  1. Home
  2. Algorithms
  3. Predicting and preventing road accidents

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.

Predicting and preventing road accidents

Municipality of The Hague

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

General information

Theme

Traffic

Begin date

Field not filled in.

Contact information

datashop@denhaag.nl

Link to publication website

https://ongevalrisico.nl/

Responsible use

Goal and impact

The purpose of the model is twofold. First, to develop effective road safety policies and reduce accidents. Second, the model can be used to compare two or more designs on road safety scores in actual projects.

Citizens ultimately see road modifications and hopefully fewer accidents.

Considerations

At the time, this was the only model examining correlations between accident rates and road, intersection or environment characteristics.

Human intervention

The outcomes are advisory to weather experts. Model outcomes are never adopted 1:1. The model is a tool for prioritising road safety policies. There is therefore no automated decision-making.

Risk management

No data that can be traced back to personal level is explicitly linked. The outcomes are assessed by an expert before use.

Legal basis

This follows from the statutory duty of the road authority and the Road Traffic Act.

Operations

Data

www.ongevalrisico.nl https://docs.google.com/presentation/d/1_Kt3_mMHhjH-KZgKJxmmqlf9rlRdJr9mgaUUBcGtBDU/edit?authuser=1#slide=id.p4 Including BGT, NWB and BRON

Technical design

Algorithm is XGBoost. Validation: AUC, ROC, confusion matrix, citizens' subjective reports on road safety.

The algorithm analyses a set of roads on which accidents have occurred and a set of roads on which no accidents have occurred. The algorithm uses 'number of accidents' as target variable (classification) and tries to find differences between properties of the two sets.

Similar algorithm descriptions

  • Accident risk

    Province of Limburg

    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

  • Risk prioritising environmental controls

    Regional Environment Agency North Sea Canal Area

    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

  • Risk-based prioritisation of data breach notifications

    Dutch Data Protection Authority

    The AP uses this algorithm to classify data breach reports by severity. Based on that classification, inspectors can prioritise serious reports. The algorithm does not contain any personal data.

    Last change on 11th of October 2024, at 9:33 (CET) | Publication Standard 1.0
    Publication category
    Other algorithms
    Impact assessment
    Field not filled in.
    Status
    In use

  • Predictive maintenance roads

    Province of South Holland

    To ensure road quality and safety, an algorithm has been developed to provide insight into road wear. The algorithm predicts required maintenance on South Holland N roads using existing historical measurements.

    Last change on 8th of November 2024, at 13:32 (CET) | Publication Standard 1.0
    Publication category
    High-Risk AI-system
    Impact assessment
    Field not filled in.
    Status
    Out of use

  • Risk prioritisation tool (RPI)

    IJsselland Environment Service

    The risk prioritisation instrument (RPI) scores companies based on objectified compliance behaviour, environmental relevance and time lapse since last inspection. The higher a company is on the list, the higher the estimated probability of violations and the impact of any occurrences on people and the environment.

    Last change on 2nd of July 2024, at 10:17 (CET) | Publication Standard 1.0
    Publication category
    Other algorithms
    Impact assessment
    Field not filled in.
    Status
    In use