The challenge

Within the Small Business Innovation Research (SBIR) program of the Dutch government, we had the opportunity to conduct a feasibility study on how Artificial Intelligence (AI) can be used to improve inclusion and empowerment in the Netherlands. This study is conducted together with Stichting Alexander: expert in participatory research for young people.

Our study is focused on the job market for young people. Unemployment among this group is the highest of the entire working population and due to the COVID-19 situation it is only getting harder and harder for young people to find a (side) job or internship. In our study we want to utilize Artificial Intelligence to scan vacancies and look for terms/sentences that discourage, or even exclude, young people to apply for a job and give these terms/sentences as feedback to employers in order to change the vacancies. By producing more attracting vacancies, young people can be motivated to apply and the job market can be made more inclusive.

Dutch – Our solution in a short pitch (2 min)

The approach

In our research we have incorporated the aspects target audience, data and product:

Target audience: together with Stichting Alexander, we organized two youth panels to get in conversation with the target audience. With them, we discussed topics like what should a vacancy look like and which elements are not attractive in current vacancies.

Data: on a sample dataset of 1000 vacancies, we applied Natural Language Techniques (NLP) to demonstrate the potential of Artificial Intelligence in vacancies by smartly searching for non-inclusive terms and sentences.

Product: to provide our target audience, but also our future partners, an idea of how our research can be translated into a product, we build a mock-up. This provides an example of how you can enter a vacancy text in a webtool and subsequently how non-inclusive words would be highlighted as well as an overview of all the vacancies and their status.

The solution(s)

In our feasibility study we concluded:

  • A solution where vacancies are improved with Artificial Intelligence is economical and technical feasible.
  • In order to make maximum impact, we should not only focus on non-inclusive terms/sentences, but also about aspects like ability to learn, clarity and understandability in a vacancy to make it attractive to young people.
  • There is little desire for a new platform with only inclusive/attractive vacancies. Our solution should connect to existing job vacancy platforms like Monsterboard, Jobbird etc. and make it easily accessible for employers to improve the vacancies they post on these existing platforms.

Impact and benefits for our client

“We believe it should go in this direction! It is looking good!” – SBIR program

Our next step is to develop a prototype solution, which companies can actually use to improve their vacancies. If we can continue with the SBIR program, we will use the next year to create a prototype and test this. To test the impact, we will both use focus groups of young people and existing vacancy platforms to conduct A/B testing.

Curious what we can do for your organisation?

Would you like to know more this case or what the Amsterdam Data Collective can do for you? Get in touch with Casper Rutjes at casper@amsterdamdatacollective.com, or check our contactpage.