An Efficient Clustering Based Feature Selection for Predicting Student Performance

Abstract

Abstract− The student failure prediction at school has turn into a very complicated challenge owing to both the large number of factors which can influence the high performance of students and the balanced nature of student's databases which are maintaining by Educational Data Mining (EDM) techniques. The main goal of this study is to detect and remove the both irrelevant and redundant features that can be used to enhance the classification accuracy in predicting the student performance. This goal is achieved by establishing the novel technique for feature or attributes selection process by hybrid of Artificial fish swarm-Cuckoo Search optimization algorithm to remove the irrelevant features or obtaining relevant features. Also, Non-negative Matrix Factorization Clustering algorithm (NMFC) performs the removal of redundant feature or attributes which are presented in the relevant features. The performance of this technique is analyzed by using the student database which comprises the gathering of student's information from different colleges. For analyzing the performance of this technique, the comparative evaluation is carried out between the classifiers used in this research such as Prism and J48 without the feature selection and classifiers with our proposed technique. The experimental consequences illustrate that hybrid of artificial fish swarm-cuckoo search optimization feature selection along with NMFC approach is accomplishing high accuracy rate than other techniques. This study facilitates us to enhance the performance of the student's failure and dropout prediction. In other words, this helps to increase the accuracy of the classification result.Keywords− Educational Data Mining (EDM), Feature Selection, Non-negative Matrix Factorization Clustering (NMFC), Artificial fish swarm, Cuckoo search optimization I. INTRODUCTION Educational Data Mining (EDM) refers the research field which is concerned with the applications that are developed by means of using data mining, machine learning and statistics for generation of information from educational settings and by using these methods the student's performance in the settings where they learn the knowledge. This EDM interests on the development of advanced tools and algorithms to realize the data patterns. EDM investigates the learning theories and updates the educational practice.Educational Data Mining (EDM) is appearing as research area with computational and psychological methods to understand the students learning performance. In modern world, EDM has the ability to log finegrained data about student's computer-based learning atmosphere which increases the significance in developing techniques to analyse the high amounts of data generated in educational settings.Generally, EDM consists of four processes [1] such as pre-processing, validation, prediction and decisionmaking. Pre-processing involves classification, regression, clustering and etc. The classified features should valid to avoid overfitting. The valid features are predicted to know about the stu...