South KoreaPublic sector2020 – ongoingKorea Employment Information Service
Competency-based AI job recommendations
KEIS reported about 19,000 people entering recommended jobs in the first half of 2026
Problem
Job matching required understanding the competencies described in resumes and vacancies.
Approach
KEIS launched AI job recommendations in 2020. The service extracted competencies from resumes and job advertisements using AI ontology technology. Subsequent updates added deep-learning and similarity-based recommendation models.
Results
Takeaway
KEIS tracked employment-insurance enrollment at recommended employers. The figures did not establish how many additional hires the recommendations caused.
Categories
- Industry
- Public sector
- Business function
- Customer service
- Innovation type
- Product and service innovation
- Adoption
- Built in-house
- Evidence
- Company's own claim
Sources
Source summaries
The release described KEIS's operating recommendation service and its model updates. KEIS reported 437,000 applicants using it and about 19,000 users entering recommended jobs in the first half of 2026.
Full details are in the original sources.