Multi-modal OCR pipeline optimized for ML training (text, figure, math, tables, diagrams)
EdOptimize is an open-source learning analytics platform for K-12 digital learning systems.
O Foul_Calculator é um aplicativo que calcula automaticamente as faltas escolares em horas, com base na porcentagem de presença do aluno.
A free, game-inspired English learning platform with structured 45-minute lessons, adaptive practice, vocabulary mini-games, and a local mentor. Proprietary freeware with an open educational data layer.
Análisis de los resultados PAES desde la Admisión 2023 en adelante identificando el ranking de los colegios.
Содержит примеры цифровых логических схем к Logisim-Evolution
An individual data analysis project in R, focusing on the educational findings in School data & Student Improvement
Automated metadata extraction pipeline for International Large-Scale Assessment (ILSA) documents using RAG-based LLM architecture. 99.2% classification accuracy across 1,622 studies.
An advanced machine learning project for analyzing student performance, utilizing sociodemographic indicators. Hosted on AWS Elastic Beanstalk for real-time predictions and integrated with AWS CodePipeline for continuous integration and deployment.
A Tableau data story that consists of multiple visualizations analyzing the relationship between marriage and education trends in the United States between 1995 and 2015, determining how each trend was impacted by economic recessions over the years, and investigating the relationship's overall impact on each state's median household income.
For this project we will attempt to use K-Means Clustering to cluster Universities into to two groups, Private and Public.. The algorithm uses unsupervised learning.
Binary classifier predicting student exam outcomes using study habits, Decision Tree: 82% accuracy, Logistic Regression comparison
Academic machine learning project predicting student academic performance for the UdeA AI4ENG Kaggle competition. Implements data cleaning and label encoding with Gradient Boosting, XGBoost, AdaBoost, and CatBoost classifiers in Jupyter Notebooks, using the Kaggle API for data download.
Creating a toy-model approach for applying Quantum Principal Component Analysis for Educational Data
Python-based Canvas API LMS Integration
Interactive dashboard and educational vulnerability index for Rio Grande do Sul municipalities using Python, Streamlit, geospatial analysis and Generative AI.
Machine Learning aplicado à predição de risco de defasagem educacional — Datathon FIAP
Leakage-safe on-time graduation classification with Decision Tree and Random Forest using GridSearchCV and a reproducible scikit-learn pipeline.
NUK Cathy Data Workspace
This depository is Case Study 1 for Doing Data Science 6306 Section 401 Tuesdays at 9:30 - 11:00 PM EST, Cohort 2017 Spring semester at SMU -- "DDS-Case-Study-1" for short. Author: Yao Yao. This project was submitted through GitHub on RStudio version 1.0.136.
To associate your repository with the educational-data topic, visit your repo's landing page and select "manage topics."