An R-based statistical inference project investigating the drivers of student academic performance. It moves beyond simple prediction to isolate statistically significant factors using multivariate regression, ANOVA, and t-tests.

A machine learning classification project that predicts student academic performance (Low/Medium/High) using behavioral and demographic data. The model analyzes 7 key features including class participation (raised hands, discussions), resource usage, parent involvement, and attendance patterns.

Achieved 100% accuracy (R²=1.0000) predicting student CGPA using Linear Regression on 1,193 student records. Discovered academic progress perfectly determines performance. Complete ML pipeline: EDA → Perfect Model.

Exploratory Data Analysis and Visualization of Student Performance using Python (Pandas, Matplotlib, Seaborn).

Predicting students performance in exams using machine learning classifiers : Logistic regression, KNN and SVM. Extraction of factors impacting students' performances.

Student performance prediction models

Student Performance (Multiple Linear Regression)

A machine learning project that predicts student final grades using classical ML algorithms on the Student Performance dataset. The dataset includes student performance data from two Portuguese schools, covering Mathematics and Portuguese language courses with demographic, social, and school-related features.

🎓 Predict student CGPA with 100% accuracy using linear regression on 1,193 records, revealing insights into academic performance and progress.

This project analyzes student performance data using Python. It explores how gender, parental education, lunch type, and test preparation affect math, reading, and writing scores. Includes data cleaning, EDA, and visualizations using pandas, matplotlib, and seaborn.