Data mining based analysis to explore the effect of teaching on student performance

Analysing the behaviour of student performance in classroom education is an active area in educational research. Early prediction of student performance may be helpful for both teacher and the student. However, the influencing factors of the student performance need to be identified first to build up such early prediction model. The existing data mining literature on student performance primarily focuses on student-related factors, though it may be influenced by many external factors also. Superior teaching acts as a catalyst which improves the knowledge dissemination process from teacher to the student. It also motivates the student to put more effort on the study. However, the research question, how the performance or grade correlates with teaching, is still relevant in present days. In this work, we propose a quantifiable measure of improvement with respect to the expected performance of a student. Furthermore, this study analyses the impact of teaching on performance improvement in theoretical courses of classroom-based education. It explores nearly 0.2 million academic records collected from an online system of an academic institute of national importance in India. The association mining approach has been adopted here and the result shows that confidence of both non-negative and positive improvements increase with superior teaching. This result indeed establishes the fact that teaching has a positive impact on student performance. To be more specific, the growing confidence of non-negative and positive improvements indicate that superior teaching facilitates more students to obtain either expected or better than expected grade.