The OECD.AI Policy Navigator

Our policy navigator is a living repository from more than 80 jurisdictions and organisations. Use the filters to browse initiatives and find what you are looking for.

GeoMatch


-
Added by:   OECD analyst
Added on:   27 Oct 2026
Updated by:   OECD analyst
Updated on:   27 Oct 2026

GeoMatch is an algorithmic tool that generates personalised recommendations on locations to settle in Canada based on client preferences and outcomes of past immigrants with similar characteristics. This tool is being tested with a subset of Express Entry applicants to identify preferred, high-opportunity settlement locations with the strongest economic outcomes based on applicants’ career-related skill sets, complementing other sources of information at their disposal.

Initiative overview

This initiative is intended to provide the following benefits:

  • Economic prosperity by supporting better economic outcomes.
  • Regionalisation of immigration by contributing to a slight redistribution of economic immigrants.
  • Provision of customised location recommendations to immigrants aligned with their location preferences.

The tool will go through a two-year study to validate the results by assessing whether clients follow the recommendations provided by the tool.

In the future, the initiative is expected to be expanded to support other lines of business at IRCC for multiple classes of applicants. The use of an algorithmic tool that generates personalised recommendations based on multiple weighted variables and historical information could have several applications across the GoC.

Results, outcomes and impacts

The tool is in soft launch, and the AI model results are being monitored, validated and optimised for the specific IRCC GeoMatch use case.

Over two years, the goal is to issue 50,000 recommendations to selected applicants to evaluate impacts on integration and earnings.

The initiative will conduct post-arrival surveys with each applicant who used the tool to validate whether applicants followed the recommendation and to gather further feedback on the tool.

Challenges and lessons learned

AI models of this specific nature (customised machine learning) require significant data to create consistently valid and optimised responses.

About the policy initiative


Category:

  • AI policy initiatives, programmes and projects

Initiative type:

  • AI use cases/projects in the public sector

Status:

  • Active

Start Year:

  • 2025

OECD AI Principles:

—

Other relevant urls:

—