Student dropout prediction using ML

Keywords: student dropout,prediction,machine learning techniques

Background

Student dropout is a significant and pervasive issue that impacts educational institutions on a global scale. It not only hampers individual academic achievement but also has far-reaching consequences for the well-being of students and societal progress as a whole. Recognizing and identifying students who are at risk of dropping out is of paramount importance in order to implement timely interventions and support systems. This research paper aims to provide a comprehensive analysis of the various factors that contribute to student dropout and explores the utilization of predictive models to accurately forecast the likelihood of dropout. To achieve this, the research begins with a systematic review of existing literature, carefully examining and synthesizing the key factors associated with student dropout. These factors encompass a wide range of elements, including socio-economic background, academic performance, engagement in school activities, social integration, family support, and psychological well-being

Aim & Objectives

Aim
The main aim of this project is predicting the academic status of a student whether the student is dropout in between in his/her study or not.
Objective
• Data Cleaning and pre-processing
• Data visualization
• Outlier detection
• Model Building

Research Methodology

Classification Algorithms like KNN, SVM, DT, AdaBoost

Software & Tools

Jupyter, Google Collab

— Preview truncated. The complete document (full chapters, references, diagrams, and appendices) is shared with clients as part of project delivery. —