Infojobs Brazil: Artificial intelligence in the pre-selection of candidates
For a job offer posted on the internet, hundreds or thousands of applications and CVs may be received.
It is a huge task to process this information in order to decide who is the right candidate. Those who have worked on it know the effort involved and, above all, the large number of candidates that have to be discarded because they do not meet the requirements.
We have developed a process based on artificial intelligence (AI) in order to automatically pre-select the most suitable candidates for a job offer, by means of an automated classification that segments candidates into two categories: suitable and unsuitable.
Infojobs is a leading private job board in Brazil, Spain and Italy. In Brazil, it is the most visited professional vacancies and talent search platform in the country, with more than 32 million visits per month and 31 million registered candidates.
Faced with this large volume of applications and registrations, InfoJobs Brazil detected the heavy workload to which its Human Resources department was exposed and the need to optimise part of its processes in order to continue offering a quality service.
Any company that handles a large volume of information can benefit from artificial intelligence to offer its customers the best user experience, displaying user products adapted to their needs, offering the most relevant information and suggesting improvement ideas to help them carry out their work more efficiently. We therefore decided that this was the best solution to address this problem.
The process
The main objective of the project was to use AI techniques to automate part of the workload of the selection process.
On the other hand, in the field of artificial intelligence, a classification problem consists of identifying to which category an observation belongs, based on a dataset containing observations whose category is already known.
The main objective of the project was to use AI techniques to automate part of the workload of the selection process.
To achieve this, we used a 180 GB dataset containing data corresponding to different categories, such as logistics, administration, arts, fashion, etc. To do this, as many models as categories were created, with the aim of making the models as specific as possible to obtain a deep and accurate classification of the candidates.
Results
- Significant reduction of the workload on your HR team, which now only analyses those profiles proposed for a vacancy that present characteristics of strong interest to the advertising company.
- Helps companies to improve their decision-making processes and make them more efficient by applying machine learning, visual computing or text analysis techniques, among others.
We are ready for new challenges
