Introduction [with Video]

One of the goals of Universities, Colleges, Institutions, and even Ed-Tech companies is to ensure Students successfully complete their Courses and thereby achieve their academic goals and be successful in the future. However, with hundreds of students in each course, it is practically impossible for Teachers and Professors to find out in advance which students are at risk of getting dropped out and may not complete their Courses. 

Student Data including performance in all kinds of Tests, Projects, Quizzes, and Assignments are continuously captured and recorded by these Institutions. This data holds huge potential to be used to find out exactly which students may drop out due to poor or inconsistent performance. This is not a ‘rule-based’ exercise and needs Statistical learning of the Data using Machine Learning models to make these predictions. 

In this Project “Prediction of Student Dropouts using Machine Learning”, we will use two very popular Machine Learning algorithms, named Naive Bayes and Decision Tree to solve this problem. These Models will be trained on Student Performance Data and the model will then be used to predict which students may potentially drop out. With this Prediction, institutions may then reach out to these students with guidance and help them to get back on track to complete their courses.