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.

Our e-services for applications, projects and assessments close on Thursday 25 April at 4:30pm because of system upgrades. We expect to open them again on Friday 26 April at 8am the latest.

MatchingID recruiting with artificial intelligence

Reference number
Coordinator MatchingID AB - MatchingID
Funding from Vinnova SEK 300 000
Project duration April 2017 - November 2017
Status Completed
Venture Innovative Startups

Purpose and goal

Our digital service will match employers and talent interest, as accurate as possible while eliminating name, picture, gender and age. The purpose of this project was to find out how AI/machine learning can make this process progressive and efficient. Now we have a concrete plan for how to make machine better than man, at achieving on point talent sourcing, with an holistic approach but without human prejudice. We have formatted data equivalent of the data a headhunter needs to match in a way so that it can be used by a self learning, self improving intelligent algorithm an AI-headhunter.

Expected results and effects

With very promising results we have mapped our how and started producing our own AI/machine learning that can analyse and learn from data and behaviours to make relevant conclusions about what makes a good match, based on both the talents and employers needs and wishes. We have met tremendous interest from universities, HR-departments, recruitment agencies, talent networks and sought after talent. Our tech team confirms, together with our other stakeholders, that we can achieve a larger visible supply of talent and improved diversity in Swedish companies.

Planned approach and implementation

Now we have determined what the least viable data need is to make the match a human headhunter does but better. We have a technical plan, a cost overview and a team to take us all the way with the AI-algorithm. We have through in depth interviews and wireframe tests confirmed that the business idea and business model as well as willingness-to-pay is viable in the market. To achieve a high quality algorithm we now need larger amounts of data and more time, so that the neural network can learn and finetune match quality. We have a database in place.

External links

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

Last updated 4 December 2018

Reference number 2017-00529

Page statistics