Validating Predictive Performance of Classifier Models for Multiclass Problem in Educational Data Mining
Classification is one of the most frequently studied problems in data mining and machine learning research areas. It consists of predicting the value of a class attribute based on the values of other attributes. There are different classifications models were proposed in educational data mining (EDM) and it is used to evaluate students academic performance in educational institutions and based on the results of the models, preventive measures to be taken in advance to enhance the students learning ability so that students academic performance can be improved. The main objective of this study is to explore different predictive measures and assess the quality of predictive performance ability of the classifier models in educational data mining.
Keywords: Overall Classification Rate, misclassification cost measure, ROC Measure, Volume Under ROC Surface, confusion matrix, Predictive Accuracy, classifier Performance.
Download Full-Text
ABOUT THE AUTHOR
Ramaswami M
Department of Computer Applications Madurai Kamaraj University Madurai 625 021 TamilNadu, India
Ramaswami M
Department of Computer Applications Madurai Kamaraj University Madurai 625 021 TamilNadu, India