Built a pipeline using stats + SHAP to detect grading bias and evaluate teacher impact via attendance and marks data. Identified sensitive attribute influence (e.g., gender/religion) on student performance using explainable AI.

An interpretable early-warning engine that detects academic instability before grades collapse. Instead of predicting performance, it models pressure accumulation, buffer strength, and transition risk using attendance, engagement, and study load to explain fragility and identify high-leverage interventions.

Simulates student activities using a simplified Probabilistic Finite Automaton (PFA) model for recommender system studies.

Analyzes student behavior patterns to understand their impact on academic performance. Provides clear visual insights and correlations from real data. Supports early prediction and decision-making for improving student outcomes.

Predicting student academic success using machine learning. Includes data preprocessing, model comparison (Random Forest, KNN), and feature importance analysis with 89% accuracy.

Normalized OULAD dataset in MySQL with secure Python ETL, constraints, roles, and analytics

A single‑page, animated dashboard built with Chart.js to showcase your 100‑student survey.

A complete Power BI Student Result Analysis Dashboard with toppers, KPIs, subject insights, mark ranges, and data modeling using Excel, Power Query & DAX.

EduTrack analyzes student performance across math, reading, and writing using Python, Pandas, and Seaborn. Through statistical insights and visualizations, it uncovers trends in gender, parental education, socioeconomic factors, and prep courses, guiding equity-focused educational strategies.

coursera scraper for structured course insights

A machine learning project to predict student final grades using academic and demographic data. Built with pandas, scikit-learn, and visualized with seaborn and matplotlib to gain insights and support early intervention for students.

A Power BI dashboard project that analyses mental health indicators among students across diverse educational programs in India.

ofsted inspection data extractor

A Tableau data visualization project analyzing student performance using the xAPI-Edu-Data dataset to uncover how absenteeism, parental involvement, and engagement metrics influence academic success.

platformă pentru studenții ase cu predicții pentru performanțe academice și analiza progresului - hostată pe un raspberry pi 5

This project predicts Ivy League admission chances using Linear, Ridge, and Lasso Regression. It includes EDA, feature engineering, assumption testing, and model evaluation, highlighting key factors like GRE, TOEFL, CGPA, SOP/LOR strength, and research experience to provide actionable insights for students and consultants.

Analysis of education process data using machine learning methods.

machine learning web app that predicts students’ math exam scores using demographic and academic factors. Built with Flask, HTML/CSS, and a Random Forest model trained on the Student Performance dataset. Interactive, insightful, and easy to use.

Predicting student performance using study hours, previous scores, sleep, practice sheets, and extracurricular participation with linear regression, Random Forest, and XGBoost in R.

Consola IA para Cuadro de Mandos CEU (OpenAI+PandasAI)