Self-efficacy (one's perceptions of their capability to perform a task) plays an important role in work-related performance and motivation. For example, self-efficacy is known to have much influence on job performance, job satisfaction, motivation, etc. As such it is important to know what factors collectively enhance the selfefficacy of employees, so that injured workers contribute to the organization they belong to after they come back to their workplace. The aim of this study is to identify such industrial accident-related factors and extract rules among the factors in order to establish self-efficacy enhancement strategies for injured workers. In this study, a binary decision tree model for self-efficacy prediction was built using a panel data provided from Korea Workers’ Compensation & Welfare Service. As a result, eight variables with the largest influence on self-efficacy were selected in the prediction model, and it correctly classified 70.1% of instances. The result suggests social support during the treatment period and offering paid time off such as vacation leave, sick leave and bereavement leave are important factors to enhance self-efficacy that will improve the work performance of injured workers.