ItalyRetail and e-commerce2019 – ongoingEsselunga
Machine-learning ranking of recruitment video interviews
Esselunga reported a 10% increase in hiring while testing AI interview rankings
Problem
Initial screening consumed recruiter time, and candidates found other jobs before interviews.
Approach
Esselunga invited applicants to recorded video interviews and tested machine learning to rank responses. Algorithms assessed language and vocal characteristics as indicators of soft skills. Recruiters retained final judgment and reviewed recordings to train the system. The traditional screening process continued in parallel during the experiment.
Results
Takeaway
The reported hiring increase did not establish the accuracy or fairness of the rankings.
Categories
- Size
- Large enterprise
- Industry
- Retail and e-commerce
- Business function
- Human resources
- Innovation type
- Process innovation
- AI technology
- Predictive analytics and ML
- Adoption
- Vendor solution
- Evidence
- Company's own claim
Sources
Source summaries
Recruiting manager Daniele Del Gobbo described algorithmic rankings with human review. He reported interview-review volumes and increased hiring.
Full details are in the original sources.
