Bicluster Analysis as an Effective Tool to Measure Students Overall Performance

In analyzing students’ performance in schools, the conventional method normally been used is known as the ranking approach. However, such a method does not take into account the different levels of performance achieved by students in different subjects at a particular time. Apart from that, the ranking approach is likely to be more sensitive to extreme values and thus may not give an accurate picture on the level of students’ performance based on various subjects. In this study an alternative approach namely Cheng and Church's biclustering algorithm was used to portray students’ profile by simultaneously grouping the students’ performance and their related subjects. By using the heatmaps, we can effectively identify specific group of students in a class who need help such as the poor performing students and their related subjects.