Published Paper Details:

Over the years the number of students dropping out of school is growing rapidly. High enrolment rates have become a major threat to many educational institutions or universities. The student enters the institution with many dreams and expectations. When expectations do not meet or certain factors such as demographics will begin to degrade them from their registered system. It is a major threat to all educational institutions. Various process of size reduction, including feature selection and feature removal. Feature selection is a step-by-step process used to select an appropriate attribute from a given attribute set. In the process of feature extraction, it involves the conversion of high-density data with low corresponding size. Feature selection includes things like academics, personal characteristics, psychological factors, health issues, teacher perspective, student behaviour. The project we introduce a student dropout prediction method by using K Nearest Neighbour, Random Forest, Naive-Bayes, Decision Tree in Python language. Student-related information is collected from a variety of sources as large data is required to predict things. The data collected contains detailed information including basic information, parental educational background, family-student relationships, community performance and student learning. Machine learning strategies are applied to selected features that target students and our main task is to apply different techniques to selected features after which to apply different metrics to each algorithm. Comparisons are made for machine learning algorithms for each metric and the model that provides the best results is considered the best. There are many factors that affect a student's ability to do school, as mentioned above. Early prediction of resignation helps an organization to keep students from the right curriculum.