Exploration of classification using NBTree for predicting students' performance

Abstract

The growth of academic data size in higher education institutions increases rapidly. This huge volume of data collection from many years contains hidden knowledge, which can assist the improvement of education quality and students performance. Students' performance is affected by many factors. In this study, the data used for data mining were students' personal data, education data, admission data, and academic data. NBTree classification technique, one of data mining methods, was adopted to predict the performance of students. Several experiments were performed to discover a prediction model for students' performance. The class labels of students' performance were students' status in study, graduates predicates, and length of study. The experiments were conducted with two-level classification, the university level and faculty level. The resulted model indicated that some attributes had significant influence over students' performance.

A Review on Predicting Student's Performance Using Data Mining Techniques

“…The attributes that have been frequently used is cumulative grade point average (CGPA) and internal assessment. Ten of thirty papers have used CGPA as their main attributes to predict students performance [5,8,9,10,3,11,12,13,14,15,16]. The main idea of why most of the researchers are using CGPA is because it has a tangible value for future educational and career mobility.…”

“…Through the coefficient correlation analysis, the result shows that CGPA is the most significant input variable by 0.87 compared to other variables [3]. Besides, in Christian and Ayub study [14], CGPA is the most influence attributes in determining the survival of students in their study, whether they can complete their study or not. In this study, internal assessment was classified as assignment mark, quizzes, lab work, class test and attendance.…”

“…Students demographic includes gender, age, family background, and disability [2,18,9,3,24,11,25,13,14]. While external assessments is identified as a mark obtained in final exam for a particular subject [5,17,19,26,27,24,28,13,29].…”

A proposed academic advisor model based on data mining classification techniques

“…In [3], the authors built a classification model to predict students" performance in higher education institute. They used the NBTree data mining classification technique and conducted several experiments to discover a prediction model for students" performance.…”

A Comparative Analysis of Selected Studies in Student Performance Prediction

“…A common approach for building such prediction models is to train a machine-learning algorithm with student performance data collected from the final years of high school combined with students' demographic data. It has been shown such data are indeed good predictors of success at a critical point such as the end of the first year of college studies ( [6], [27], [28], [29], [30], [31], [32], [33]). However, much of the demographic data seldom changes and academic performance history from earlier years never does.…”