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.

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.

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

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

🎓 Student Performance Prediction System using Machine Learning & Streamlit to forecast next semester CGPA with interactive insights and real-time predictions.

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.

📊An end-to-end Power BI analytics dashboard providing deep insights into Indian Higher Education. Visualizes college distribution by region, management type, student enrollment strength, and course offerings across multiple states and cities.

📊 Analyze student performance with this interactive Power BI dashboard featuring KPIs, insights, and detailed documentation for easy replication.

Analyzes chronic absenteeism as an early risk signal for district-level graduation outcomes using CRDC and EDFacts data, emphasizing interpretability and prioritization.

Cloud-ready analytics platform for student retention | ETL → Time-aware ML → SHAP → BI marts → A/B simulation → ROI modeling

A Power BI dashboard analyzing online course sales, enrollment trends, student demographics, revenue performance, completion rates, and instructor effectiveness for an e-learning platform.

Multi-year benchmark analysis comparing EHCP phonics attainment in Medway against national averages, highlighting persistent performance gaps and system-level risk factors.

Predicting student performance using Machine Learning and educational data analytics.

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

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

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.

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.

coursera scraper for structured course insights

Data Warehouse & Business Intelligence project analyzing gender parity in European higher education (2013–2023) using Power BI, DAX and Eurostat/PORDATA data.

End-to-end supervised ML pipeline for student performance and dropout prediction. Features data preprocessing, feature engineering, multi-model training, performance comparison, model persistence, and reproducible project structure with detailed README files.

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

Machine Learning app predicting Student GPA based on study habits, attendance, and parental support. Built with Streamlit and Scikit-Learn to help educators identify at-risk students.

Data analysis project uncovering what truly drives hiring decisions — skill, preparation, or candidate profile — using real interview evaluation data.

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.

SQL model to assign ECTS grades (A–E) from GPA percentiles per degree group. Includes data contract, validation tests, and a production-ready view version (MySQL 8+/portable SQL). Designed for analytics/reporting pipelines and reproducible student performance benchmarking.

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.

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

Machine learning project to identify students at risk of academic burnout using behavioral and academic data.

No description provided.