Technological Role Classifier in Computer Science by Analyzing Psychological Profiles and Technical Skills with Machine Learning and Deep Learning

Calderón M.; Ramos G.; Ticona W. · Lecture Notes in Networks and Systems (2026) · DOI: 10.1007/978-3-032-20749-4_6

Resumen

Effective career guidance for computer science students is a crucial challenge, given the increasing demand for specialized technological careers. This study proposes a predictive system based on machine learning and deep learning to identify the most suitable career role for each student, considering their technical skills and psychological characteristics. The process used the CareerMap dataset of 9,180 records and included preprocessing, normalization, feature selection, and modeling. Three methodological approaches were com-pared: (1) machine learning models with classical feature selection, (2) pure deep learning models, and (3) hybrid deep learning + machine learning models. The best results were obtained with the SVM model (F1 score: 0.9994) using mutual information and Boruta, and with the DCN model (F1 score: 0.9988) using the deep learning methodology. The results demonstrate that the right combination of feature selection and modeling techniques allows for highly accurate prediction of optimal job roles and provides a valuable tool to support job placement and reduce career disorientation in the technology sector. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

Instituciones: Universidad ESAN; Universidad Tecnológica del Perú