Support System for the Recruitment and Selection Process Using the Sbert Model

Arellanos D.E.H.; Silverio A.M.M.; Alarcon J.S.D. · International Conference on Artificial Intelligence, Computer, Data Sciences, and Applications, ACDSA 2026 (2026) · DOI: 10.1109/acdsa67686.2026.11468072

Resumen

The growing adoption of artificial intelligence in the business sector has driven the development of intelligent systems aimed at optimizing critical processes such as recruitment and personnel selection. This research aims to develop a system based on automated data processing using SBERT, capable of accurately and quickly identifying the most suitable profiles, reducing human effort and biases in decisionmaking. The system development included the selection of tools, the construction of a structured test dataset based on real résumés, the development of a semantic similarity model, the implementation of a functional web application, and its subsequent validation using metrics. The results showed a significant improvement in accuracy and a reduction in selection time, decreasing from 50 to 20 minutes per position, representing a 60% reduction. The average similarity exceeded 0.70, demonstrating the system's effectiveness in identifying compatible candidates quickly and objectively. It is concluded that artificial intelligence is an effective strategy to optimize the selection process in Peruvian organizations.

Instituciones: Universidad Peruana de Ciencias Aplicadas