A Novel Approach to Tackle and Predict Absenteeism of Students Using Deep Learning and Data Analytics

Many pupils miss a lot of school each day along with many people in the corporate world. There are many reasons for absences, and they can come from inside and outside of the school. Motivational reasons for absenteeism include cases when a student may not want to go to class; these absences are typically voluntary and intentional. Other absences, however, are structurally based, meaning that students must skip class because of their living circumstances (such as needing to relocate frequently), and are therefore out of their control and are a result of an unavoidable circumstance. There are many different and connected reasons why students miss class. While absenteeism can frequently spike and then diminish, certain kids may fall victim to a vicious cycle of absences. The school, the absentee’s family, and the absentee themselves are frequently divided into three groups in academic literature when discussing absenteeism’s causes. When a child moves from elementary to high school, absenteeism frequently starts in the lower grades and gets worse. A teen could experience alienation in a new school and struggle to build relationships with instructors and other pupils. A student could decide not to go to school if it is too crowded or physically unsound. Bullying, an uninteresting curriculum, academic failure, and the sense of harsh behavioral sanctions are among more school-related reasons for absence. Most of these absences are mainly motivated, meaning that the student voluntarily chooses to skip class.The motive for the research is to find that the student might be absent due to which reason and what can be done to stop that using data analytics and deep learning techniques such as deep neural network and convolutional neural network.