Student Dropout Prediction System built using machine learning classifiers (KNN, Logistic Regression, Decision Trees, Random Forest, SVM, Naive Bayes). Built with Python and Flask, this system predicts dropout risks based on student data to improve retention rates

Predict and monitor student dropout risk using Machine Learning and Business Intelligence. Includes a Streamlit app for real-time prediction and a Metabase dashboard for academic insights.

Machine Learning Approach to Predict Student Dropout and Academic Achievement – A data visualization and analytics project using Looker Studio to uncover patterns and factors contributing to student dropout rates. This project was completed as part of the final exam for the Introduction to Big Data Analytics course (INSY 8413)

This project comprehensively tackles student dropout at a higher educational institute. It aims to not only accurately predict student final status but also to map relationships and identify key factors driving dropout, leveraging machine learning, specifically the robust and accurate RandomForest algorithm.