DROPOUT PREDICTION OF HIGHER EDUCATION STUDENTS THROUGH EDUCATIONAL DATA MINING

In recent years, there has been a substantial increase in the number of students who quit attending educational institutions altogether. Numerous educational establishments and colleges are facing a significant challenge because of the rising number of students who withdraw from registered classes. The student comes to the educational establishment carrying a great deal of hope and anticipation with them. If their expectations are not met or if certain variables, such as demography, have an effect on them, it may cause them to withdraw from the programme for which they have registered. It poses a significant risk to each and every educational establishment. Dimensionality reduction can be accomplished by a variety of methods, two of which are feature selection and feature extraction. The process of selecting features, also known as feature selection, involves going through a series of steps in order to choose the appropriate attribute from among a group of available attribute sets. The process of extracting features requires transforming data with higher dimensions into data with lower dimensions matching to those higher dimensions. Aspects such as academics, demographics, psychology, health concerns, the opinion of the instructor, and student behaviour are taken into consideration throughout the feature selection process. In this article, we present a method for predicting student attrition using the Naive-Bayes Classification Algorithm implemented in the R programming language. In addition, it investigates the factors that contribute to a student's early withdrawal from school and attempts to forecast whether or not the student will do so. As was just discussed, a student's decision to stop attending school might be influenced by a wide variety of different reasons. The organisation is better able to keep students enrolled in the appropriate academic programme as a result of early dropout prediction.