Abstract :

According To Global Reports, More Than 70% Of Students Rely On AI (Artificial Intelligence) Tools For Academic Purposes, While 65% Experience Challenges In Balancing Productivity And Engagement In Their Learning Journey. Existing Manual Academic Monitoring Methods Often Fail Due To Inconsistent Evaluation, Limited Personalization, And The Inability To Capture Real-time Changes In Student Behavior. To Address These Limitations, The Proposed Approach Introduces An AI-powered Student Life Exploration Framework Using Curated Datasets Containing Academic Activity Records, Behavioral Logs, And Feedback Scores. The Dataset Undergoes Structured Preprocessing To Handle Noise, Imbalance, And Irrelevant Attributes, Followed By EDA (Exploratory Data Analysis) To Derive Patterns In Student Behavior. The System Is Designed To Predict The Final Outcome Of Student Performance, Classifying Engagement Into Categories Such As Assignment Completed, Confused, Gave Up, And Idea Drafted, Using Multiple Classifiers Including Logistic Regression (LR), Decision Tree (DT), Gradient Boosting (GB), Proposed Tao Learned Extra Trees (ET), And AdaBoost (AB). Similarly, Satisfaction Rating Prediction Is Enabled To Classify Students’ Satisfaction Levels Into Low (1–2), Medium (2–4), And High (4– 5). The Trained Models Are Automatically Stored For Future Predictions, Ensuring Scalability And Reusability. The Final Framework Not Only Improves Prediction Accuracy But Also Enables Batch Prediction Through CSV Uploads For Large-scale Records, Ensuring Real-time Student Monitoring. This Comprehensive System Ensures A Strong Foundation For Predicting Engagement, Enhancing Personalized Feedback, And Improving Overall Productivity In The Educational Ecosystem.

Published:

27-3-2026

Issue:

Vol. 26 No. 3 (2026)

Page Nos:

745-753

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite