Your browser doesn't support javascript. This means that the content or functionality of our website will be limited or unavailable. If you need more information about Vinnova, please contact us.

Predicting moving patterns using gravitational models and AI

Reference number
Coordinator Statistikkonsulterna Jostat & MR Sample AB
Funding from Vinnova SEK 344 313
Project duration December 2020 - August 2021
Status Completed
Venture AI - Competence, ability and application
Call Start your AI-journey for businesses - autumn 2020

Important results from the project

** Denna text är maskinöversatt ** The goal is to make AI / ML available in a rational and efficient way together with the gravity model so that predictions can be made more accurate. The assessment is that through the project we have been able to apply and develop the methods and that we are well prepared to market services in the area. The results have been presented at a scientific conference and will be marketed among municipalities and regions in Sweden during the autumn.

Expected long term effects

** Denna text är maskinöversatt ** The project has been able to show that it is possible to apply Artificiella Neurala Nätverk (ANN) to migration data and thus - in some cases - create better estimation results. These results can lead to better and more accurate predictions to use in community planning.

Approach and implementation

** Denna text är maskinöversatt ** The project has modeled data from public sources, Statistics Sweden, KOLADA, Google Maps, Lantmäteriet and others. We have applied the gravity model and applied traditional methods, poisson regression, and AI / ML methods (Artificiella Neurala Nätverk (ANN)). The analyzes have been made available with different analysis and visualization methods. We have also studied how the results can be used to further enrich surveys that have been conducted with telephone and postal surveys.

The project description has been provided by the project members themselves and the text has not been looked at by our editors.

Last updated 15 October 2021

Reference number 2020-04063