AI Based Drop-Out Prediction and Counselling System
Chanthrika R, IV year CST, SNS College of Engineering, Coimbatore. Email: chanthrika045@gmail.com
Muthuganesh S, IV year CST, SNS College of Engineering, Coimbatore. Email: muthuganeshmg2004@gmail.com
Sanjhana SP, IV year CST, SNS College of Engineering, Coimbatore. Email: sanjhanaxx22@gmail.com
Shirivanth P, IV year CST, SNS College of Engineering, Coimbatore. Email: shirivanth2909@gmail.com
Kalaivani K, AP/CST, SNS College of Engineering, Coimbatore. Email: kalaivani.k. csd@snsce.ac.in
Abstract: The AI-Based Dropout Prediction and Counselling System is a cutting-edge project that aims to reduce student dropout rates with the help of artificial intelligence. Dropout is a significant problem faced by the education sector and can be attributed to several causes such as underperformance in their courses, poor attendance, financial issues, or personal stress. The system makes use of machine learning algorithms to analyze various data sources, including attendance, grades, socio-economic data, short- and long-term engagement in school activities, and behavioral patterns. It is able to predict with a high level of accuracy the likelihood of student dropout, with other models identifying unseen trends and risk factors.
In addition to prediction, the strength of the project is in the area of intervention. The system develops an individualized counselling strategy once a student is identified as "at risk", which may involve academic mentoring, remedial classes, psychological support, guidance for scholarships and financial support, and/or career counselling. The recommendation engine will provide actionable insights to teachers, counsellors and administrators in a timely manner to support students in need of interventions. The system also provides a dashboard for visualization of student data and retention statistics, which allows institutions to observe trends over time and measure the effect of interventions. Other ethical issues related to privacy, fairness, and providing predictions that are free from bias are taken into account to ensure the well-being of flexible education.
Keywords: Artificial Intelligence, Machine Learning, Academic Performance, Attendance, Financial Difficulties, Personal Stress,Behavioral Trends,Mentoring, Psychological Support, Remedial Classes.
