An empirical study on attribute selection of student performance prediction model

Abstract

Despite improvement in the standard of education globally, students' failure rates have risen. Data mining has been implemented in several domains, including education, for extracting valuable information from raw data. The aim of this study was to develop a model for predicting student performance and thereby identifying the students who might under perform in examinations. Student data used for the study consisted of demographic and academic information of students. Systematic analysis of different attributes of the student data was done using feature subset selection algorithms. The model was tested using classification algorithms. Based on these results a small attribute set, namely student data feature set (SDFS) was proposed. The experimental results demonstrate that the learning model using SDFS gives the best results and also minimises the errors. This model can be utilised to identify the academically weaker students so that appropriate preventive action can be taken to avoid failures. Adoption of data analytics in education can help create a smart education system beneficial for society.