BEHAVIORAL DIGITAL TRACES AS A SOURCE FOR EVALUATING THE EFFECTIVENESS OF PERSONNEL TRAINING PROGRAMS

Abstract

The purpose of this article is to examine the potential of behavioral digital traces generated by learning management systems as an instrument for evaluating the effectiveness of personnel training programs. The relevance of this study is driven by a growing gap between the volume of behavioral data accumulated in corporate LMS platforms and the limited capacity of organizations to utilize these data for evidence-based assessment of training outcomes. Traditional evaluation models, were developed within an offline paradigm and primarily rely on self-reported measures, which restricts their applicability in the context of digital learning environments. The research methodology combines systematic literature review with conceptual modeling. The study synthesizes findings from three converging disciplines: learning analytics, HR analytics and people analytics, and training evaluation theory. Based on this synthesis, the authors develop a conceptual framework that maps specific types of behavioral digital traces to established evaluation levels. The results demonstrate that behavioral data from LMS platforms, including login frequency, session duration, content interaction patterns, assessment attempt sequences, and module revisitation behavior, constitute valid indicators of learner engagement, knowledge acquisition, and behavioral change. The proposed framework integrates these indicators into a structured evaluation system that complements traditional survey-based approaches with objective, continuously collected digital evidence. The study identifies that while learning analytics has matured significantly in higher education settings, its application within corporate human resource development remains fragmented and theoretically underdeveloped. The practical value of this research lies in providing HR professionals and L&D managers with a systematic approach to leveraging existing LMS data for training evaluation purposes, thereby reducing reliance on costly post-training surveys, enabling real-time monitoring of learning effectiveness, and supporting data-driven decisions regarding personnel development investments. The findings contribute to bridging the gap between learning analytics and people analytics disciplines within the broader context of HRM digitalization.