A Comparative Analysis on the Evaluation of Classification Algorithms in the Prediction of Students Performance

Objectives: Data mining techniques are implemented in many organizations as a standard procedure for analyzing the large volume of available data, extracting useful information and knowledge to support the major decision-making processes. Data mining can be applied to wide variety of applications in the educational sector for the purpose of improving the performance of students as well as the status of the educational institutions. Educational data mining is rapidly developing as a key technique in the analysis of data generated in the educational domain. Methods: The aim of this study presents an analysis of final year results of UG degree students using data mining technique, which carried out in three of the private colleges in Tamil Nadu state of India. The primary objective of this research work is to apply the classification techniques to the prediction of the performance of students in end semester university examinations. Particularly, the decision tree algorithm C4.5 (J48), Bayesian classifiers, k Nearest Neighbor algorithm and two rule learner’s algorithms namely OneR and JRip are used for classifying the performance of students as well as to develop a model of student performance predictors. Results: The result of this study reveals that overall accuracy of the tested classifiers is above 60%. In addition classification accuracy for the different classes reveals that the predictions are worst for distinction class and fairly good for the first class. The JRip produces highest classification accuracy for the Distinction. Classification of the students based on the attributes reveals that prediction rates are not uniform among the classification algorithms. Also shows that selected data attributes have found to be influenced the classification process. The results showed to be satisfactory. Improvements: The study can be extended to draw the performance of other classification techniques on an expanded data set with more distinct attributes to get more accurate results.