Instructional design for Web-based teaching and learning environments causes problems for two reasons. Firstly, virtual forms of teaching and learning result in little or no direct contact between instructor and learner, making the evaluation of course effectiveness difficult. Secondly, the Web as a relatively new teaching and learning medium still requires more research into learning processes with this technology. We propose data mining – techniques to discover and extract knowledge from a database – as a tool to support the analysis of student learning processes and the evaluation of the effectiveness and usability of Web-based courses. We present and illustrate different data mining techniques for the evaluation of Web-based teaching and learning systems.