Direct naar content

You are here:

  1. Home
  2. Algorithms
  3. Youth welfare forecast model

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.

Youth welfare forecast model

Municipality of Amersfoort

The algorithm predicts the number of clients who will use youth care in the coming quarters/years.

Last change on 6th of March 2024, at 15:36 (CET) | Publication Standard 1.0
Publication category
Other algorithms
Impact assessment
Field not filled in.
Status
In development

General information

Theme

Health and Healthcare

Begin date

Field not filled in.

Contact information

algoritmeregister@amersfoort.nl 

Responsible use

Goal and impact

The model provides an estimate of client numbers with an unchanged policy. With this information, policy changes can be made in time to adjust undesirable high/low client numbers (on specific youth care forms). The impact of the algorithm on citizens is low. No personal data are used, only aggregated client numbers at the level of the entire city (no breakdown by neighbourhood/neighbourhood, for example). In decision-making around policy, this model has no decisive role it only provides insight alongside other sources of qualitative and quantitative information.

Considerations

The model can provide a good estimate of expected client numbers, where other sources often only provide insight into the present/past.

Human intervention

The algorithm does not provide a judgement or advice. It provides an insight that can be used alongside other insights (such as reports on current and historical client numbers). In doing so, the algorithm gives an estimate of the likely accuracy of the forecast, with this it can be chosen to ignore forecasts with a large margin of error.

Risk management

Field not filled in.

Legal basis

Youth Act

Operations

Data

Only aggregated client data sourced from municipal care records

Technical design

This is a mathematical model that uses autoregressive techniques. This means that client numbers are predicted entirely on the basis of past fluctuations and trends of this data. Thus, no other data are used to forecast with. The specific techniques used are ARIMA and exponential smoothing (Holt-Winters).


The model's performance is calculated based on its prediction of the past 2 quarters. These quarters are left out of the training set and used as a test set. The model's prediction on these quarters is compared with the observed numbers. The deviation between these data is shown in the final product as a percentage. For product groups with many clients, this deviation is often around 1%; for product groups with few clients, this percentage can be higher.

Similar algorithm descriptions

  • Care profile algorithm

    CIZ Centre for Healthcare Indication

    The algorithm helps the CIZ employee choose the care profile that best suits the client's care needs. A care profile states what care a person needs.

    Last change on 31st of October 2024, at 16:40 (CET) | Publication Standard 1.0
    Publication category
    Impactful algorithms
    Impact assessment
    Field not filled in.
    Status
    In use

  • Prediction model Youth Aid

    Municipality of The Hague

    The Youth Aid prediction model predicts the number of unique young people with Youth Aid without a stay with a six-year prediction horizon. Besides the number of young people, predictions are also made on costs. Predictions are made at district level, for city districts and for all of The Hague.

    Last change on 5th of July 2024, at 11:06 (CET) | Publication Standard 1.0
    Publication category
    Other algorithms
    Impact assessment
    Field not filled in.
    Status
    In use

  • Reference estimate

    Ministry of Education, Culture and Science

    Forecast of national numbers of pupils and students in the Dutch funded education system

    Last change on 8th of October 2024, at 7:16 (CET) | Publication Standard 1.0
    Publication category
    Other algorithms
    Impact assessment
    Field not filled in.
    Status
    In use

  • Profile Frequent movers National Approach to Address Quality (LAA)

    National Authority for Identity Data

    The algorithm selects addresses where at least one person is registered with a large number of address changes in a relatively short period of time.

    Last change on 27th of May 2024, at 12:02 (CET) | Publication Standard 1.0
    Publication category
    Impactful algorithms
    Impact assessment
    Field not filled in.
    Status
    In use

  • Covid-19 model

    National Institute of Public Health and the Environment

    A projection model translating incoming data on the Covid epidemic into a forecast of the number of ICU admissions per day with COVID-19 in the Netherlands, during the COVID pandemic.

    Last change on 17th of June 2024, at 11:37 (CET) | Publication Standard 1.0
    Publication category
    Other algorithms
    Impact assessment
    Field not filled in.
    Status
    Out of use