Data Mining In Higher Education: Students Dropout Assessment “A Case Study on Aps University” | Original Article
In this paper, I apply different data mining approaches for the purpose of examining and predicting students’ dropout through their college programs. For the subject of the study, I selected total 1295 records of various stream students graduated from APS University between years 2013 to 2015. For this purpose, the preliminary data of 1295 students collected in prescheduled (Schedule and questionnaire) format of personal interview to find out the reasons of dropout from college. In order to classify and predict dropout students, different classifiers have been trained on my data sets including J48 Decision Tree and PART classification. These methods were tested using 10-fold cross validation. The accuracy of J48, and PART classifiers were 77.33 and 75.13 respectively. The study also includes discovering hidden relationships between student dropout status and enrolment persistence by mining a frequent cases using algorithm. The reasons recorded for dropout of students at this university were viz Agriculture work, Care of sibling, Poor economic condition, Lack of education facility, Ignorance of guardian, Long illness, Non friendly environment of college being to for away, no adult protection. The information generated will be useful for better planning and implementation of educational program and infrastructure under measurable condition to find out the main reasons of dropout students in various colleges at this university.