Purpose: This paper aims to explore predicting employee learning activity via employee characteristics and usage for two online learning tools. Design/methodology/approach: Statistical analysis focused on observational data collected from user logs. Data are analyzed via regression models. Findings: Findings are presented for over 40,000 employees' learning activity for one year in a multinational technology company. Variables including job level and tool use yielded a predictive model for overall learning behaviors. In addition, relevant differences are found for managers and nonprofessional learning. Research limitations/implications: Importantly, how well employees learned content was not measured. This research is also limited to observational relationships: for example, the online tools were used by self-selected users, instead of randomly assigned. Future research which randomly assigns tool use to employee subgroups could explore causal relationships. Practical implications: This paper presents implications for business analysts and educational technology: how predictive analytics can leverage data to plan programs, the significant challenges for the adoption and usage for online learning tools, and the distinct needs of managers engaging with these tools. Originality/value: Given a growing emphasis on using employee data, it is important to explore how learning behaviors can be made visible in people analytics. While previous research has surveyed employee cultures on learning or explored the socio-psychological factors which contribute to this learning, this paper presents novel data on employee participation in learning programs which illuminates both how HR metrics can productively use this data to reify learning patterns, and how workplace technology designers can consider important factors such as internal hierarchies.