This study investigated an innovative approach of program evaluation through analyses of student learning logs, demographic data, and end-of-course evaluation surveys in an online K–12 supplemental program. The results support the development of a program evaluation model for decision making on teaching and learning at the K– 12 level. A case study was conducted with a total of 7,539 students (whose activities resulted in 23,854,527 learning logs in 883 courses). Clustering analysis was applied to reveal students’ shared characteristics, and decision tree analysis was applied to predict student performance and satisfaction levels toward course and instructor. This study demonstrated how data mining can be incorporated into program evaluation in order to generate in-depth information for decision making. In addition, it explored potential EDM applications at the K- 12 level that have already been broadly adopted in higher education institutions.