Prioritizing incoming leads at a Belgian Interim company


Prioritizing incoming leads at a Belgian Interim company

Vivaldis is a Belgian interim office providing recruiting services to SMB companies.

Founded in 1991, Vivaldis recently opened their 71st office with a few more to come in the near future. Vivaldis searches for their customers the perfect job candidate for a certain vacancy. They are specialized in the construction business, Maritime & Logistics and Office employees.


Vivaldis is helping companies in filling 8.000 jobs yearly with the ideal candidate. In order to do so, Vivaldis can rely on the expertise of their advisors to reflect on a resume & evaluate which match they might have with which job. Currently, candidates are processed randomly meaning that no priority is set to process high-value candidates first or evaluate the candidates based on a level of urgency.

Therefore, Vivaldis was looking to improve this job search process by finding a way to rank the candidates who are most likely to find a job. This way, employees can spend their time on scanning the resumes of the most promising candidates.


Vivaldis asked element61 to improve the efficiency of the job search process.

In order to scan the most relevant resumes, we have built a machine learning model which predicts which candidates are most likely to be matched with a job. The employees can then scan through the most relevant resumes and as such, tackle high value candidates as fast as possible. At this point, the machine learning model is not scoring the candidates for a specific job but rather the overall employability of a candidate.

In order to define a score, we consider different drivers for the employability score such as age, language knowledge, education level, driving permit, experience, etc. Important when working with sensitive data, is that the model is built to avoid any discrimination or bias. Among others, this means we don’t include certain drivers like gender & region. The tooling developed is working hand-in-hand with Salesforce, the customer tool in place to collect and store all the information about the candidates (both information received in the offices as on the website itself). This means that Salesforce remains the end-user tool & embeds our solution.

Technically, element61 decided to expose our solution as an API. Every week, we retrain the machine learning model. 


element61 helped Vivaldis to optimize the job searching process by creating an employability score for each of the candidates.

By ranking the candidates based on that score, Vivaldis can more efficiently scan through all the resumes.

This results in a 3 times more efficient way of working. Special attention was paid while building the model to avoid a bias or discrimination.