Student Performance Analysis with Using Statistical and Cluster Studies

Abstract

Education is the backbone and significant factor in development of a country. The research on education system and performance of student’s learning are very important for educational institutions and government to make decisions on quality education. This study analyzes the student’s performance by using statistical and unsupervised machine learning (hierarchical and k-means) algorithms. These statistical reports are useful for student’s educational strategies and their performance. As per statistical reports, one student education is mainly dependent on the family background, his personal profile, and his activities. Interestingly, some of factors like alcohol consumption, outing (going outside with friends), and romance are also impacted on his education and his result. The unsupervised machine learning algorithms like k-means and hierarchical cluster studies give the good results for predicting performance (pass or fail) of the student. The hierarchal cluster study projects the cause of pass and failure of students by different factors like family size, alcoholic consumption on working days and weekends, address (rural/urban), sex (male/female), and student regularity.