Wmo forecasting model

Municipality of The Hague

The Wmo forecasting model provides a prediction of the number of unique users and costs of Wmo with a six-year forecast horizon. Predictions are made at district level for both the Wmo total and sub-products of the Wmo (Help with Household, Support at Home and Assistive Technology and Services).

Last change on 23rd of August 2024, at 14:10 (CET) | Publication Standard 1.0

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

General information

Theme

Social Security

Begin date

Field not filled in.

Contact information

[e-mail]

Responsible use

Goal and impact

The algorithm was developed because the municipality wants to have more insight into the use and costs of Wmo in the coming years. The population of The Hague is growing and ageing, as a result of which the use of Wmo is also expected to increase. The question is by how many people and in which districts of The Hague and for which Wmo facilities? The forecasting model answers these questions.

Considerations

No alternatives were considered to achieve the goal.

Human intervention

There is no automated system. The insights from the prediction model can only be used through human intervention and with the context knowledge and experience of employees involved.

Risk management

The risks of the algorithm were identified in advance and during the construction of the prediction model. Because the prediction model does not make statements about individuals but about the use of facilities in neighbourhoods, there was no risk that the results from the model could violate the privacy of specific individuals. Furthermore, we only worked with neighbourhoods that were sufficiently large (more than 100 inhabitants) and where enough people used the Wmo (more than 100 users). One reason for this is that it does not allow for disclosure. That is, by combining characteristics, we cannot identify who the potential users of Wmo facilities are. Furthermore, when building the model, we weighed up together with the privacy officer which variables could and could not be included from a privacy perspective. Here, the AVG was always the starting point. In addition, explainability of the model and the results is a relevant and decisive criterion. Finally, Utrecht University's The Ethical Data Assistant was used to identify possible ethical problems in advance. This led to the drafting of an ethical framework. The question of what role bias plays in the use of the algorithm is far too general a question, as there are many forms of bias. If it is bias aimed at specific population groups, it does not play a role in this model. We are not looking for specific individual people with specific characteristics, but want to estimate the use of Wmo in the whole neighbourhood and for all of The Hague.

Legal basis

There is no legal basis for the forecasting model, but the municipality is responsible for implementing the Wmo and the model allows the municipality to better anticipate expected developments and better support citizens.

Operations

Data

Only open data was used, namely the file Kerncijfers Wijken en Buurten CBS and the file Wmo-cliënten; type maatwerkarrangement CBS.

Technical design

A regression model is used to estimate the relationship between Wmo use and predictors. This involves searching for the characteristics with the smallest prediction error (determined using the measures: RMSE, MAE and MAPE). The characteristics best able to predict Wmo use are used for forecasting. Forecasts are made within a prediction interval of 80 per cent.