AI-Enabled Workforce Competency Mapping in Public Transport

Abstract

Artificial intelligence (AI) is transforming modern Human Resource Management (HRM) by automating administrative procedures and providing data-driven insights into employee capabilities. Within public transport systems—where operational decisions span fleets, depots, customer interfaces, and administrative units—aligning workforce competencies with dynamic technological demands is essential. This study presents a quantitative framework that combines multiple linear regression and machine learning algorithms to map workforce competency preparedness and optimize training resource allocation. Using empirical data collected from operational, technical, supervisory, and customer-facing staff (N=397) across the Andhra Pradesh State Road Transport Corporation (APSRTC), we evaluate six core competency drivers: AI readiness, digital literacy, operational analytics competence, safety and compliance competence, learning agility, and institutional support. Multiple regression results indicate that all six drivers significantly influence competency preparedness (), with operational analytics competence () and safety and compliance competence () exerting the strongest standardized effects. Furthermore, comparative machine learning classification demonstrates that Logistic Regression (, Accuracy ) and Naïve Bayes () effectively categorize employees into low, moderate, and high training priority levels without circular prediction error. The study provides human resource practitioners and mobility policy-makers with an empirical, non-punitive decision support model for target-oriented workforce development.