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.
Forecast crowds and ballot paper usage at polling stations
- Publication category
- Impactful algorithms
- Impact assessment
- Field not filled in.
- Status
- In use
General information
Theme
- Organisation and business operations
- Law
Begin date
Contact information
Responsible use
Goal and impact
For signalling potential crowding and related ballot consumption. The algorithm scores normal, quiet and busy. This score is visible on the Queue app for the public. In addition, the election control room uses the data to advise the polling station chairman on additional ballot papers needed. It can also be decided by the polling station chairperson to refer people to another polling station.
Considerations
First version was a count of the actual number of visitors in the Polling Station as input for stock control of the number of ballot papers. This did not work as well.
Human intervention
The algorithm can be stopped in the app at any time and replaced by counts by Polling Station members. As for the process, the Control Room decides to post ballot papers and can also decide not to do so. The crowding indicator in the QueueApp can use data from the algorithm but also data entered by Polling Station members.
Risk management
There is no risk because the voter decides which polling station to visit. There is no automated decision-making. Bias does not play a role because the number of voters is counted independently of personal data.
Legal basis
Electoral Act
Operations
Data
The Polling StationApp records that people voted but not who. The numbers are used for the algorithm.
Technical design
Hourly averages, historical curves over time and linear regression. Based on the turnout in the first three hours of opening of each polling station (source Polling StationApp), the hourly average per polling station is calculated and then a forecast is made for each polling station over the next 10 hours. For crowding, categorisation is made to Normal, Average and Crowded based on historical turnout curves for all polling stations, in the categories Small, Ordinary, Large, Extra Large. For ballot paper consumption, a linear forecast is made based on usage.
Similar algorithm descriptions
- The Polling Station Manager allows volunteers to sign up to help with elections. The volunteer's experience determines which roles are available and what training is needed to perform these roles well.Last change on 18th of July 2024, at 12:56 (CET) | Publication Standard 1.0
- Publication category
- Other algorithms
- Impact assessment
- Field not filled in.
- Status
- In use
- This algorithm, the forecasting model, provides insight into future peak moments at the municipality's Citizen Affairs desks. This allows additional staff to be hired in time for expected peak moments. This model also supports financial planning.Last change on 27th of June 2024, at 13:10 (CET) | Publication Standard 1.0
- Publication category
- Other algorithms
- Impact assessment
- Field not filled in.
- Status
- In use
- The Polling Station Manager allows volunteers to apply to help with elections. A volunteer's experience determines which positions are available and what training is needed to perform these positions well.Last change on 14th of January 2025, at 10:39 (CET) | Publication Standard 1.0
- Publication category
- Other algorithms
- Impact assessment
- Field not filled in.
- Status
- In use