Seven dry-bean varieties from real morphology features with duplicate-aware splits, calibrated SVM and held-out error analysis

AI study roadmap 2026: learn AI engineering by building — one track, stage by stage, zero spend on LLM APIs

Your AI data science team, with the receipts. Multi-agent analysis with deterministic verification and human review. Ask data questions in plain English; agents run the stats, a verifier checks the numbers, people decide.

Top Distributed Training Optimization (Opensource) Star if you like it!

A config-as-graph framework for deep learning: any pipeline, in any modality or domain, assembled from swappable components.

Adaptive focused web crawler with GraphUCB-CD bandit + change-point detection. Research-grade, reproducible offline benchmark.

A programming language for AI and data work with plain-English syntax, a tensor engine with autograd, a Python bridge, and a package manager.

Andrew Ng Deep Learning, an educational AI resource designed to break down foundational neural network concepts, machine learning algorithms, and model optimization techniques. It provides a seamless user experience to help students and AI practitioners build strong deep learning fundamentals and master core data science principles.

Credit risk system with machine learning

ML-based network intrusion detection: scores network flows, flags attacks, maps alerts to MITRE ATT&CK, with a secured scoring API and dashboard.

Weka Explorer in your browser: 25 classifiers matching Weka 3.8.7, clustering, association rules, attribute selection, visualization and PDF reports in plain HTML/CSS/JS. Plus responsible web-data import and a bilingual EN/EL AI assistant with on-device models (Needle 2, Whistle, MobileCLIP).

A machine learning application that detects spam emails using text preprocessing, TF-IDF features, and classification algorithms.

Credit card fraud detection at 0.17 % prevalence, evaluated the way a fraud team would: alert budget, simulated cost, temporal split, bootstrap intervals.

An Intelligent Logistics Analytics, Route Efficiency, and Predictive Decision Support System for Confectionery Freight Networks with Multi-Model Machine Learning and Real-World Geospatial Mapping.

Plataforma brasileira de inteligência financeira, em fase de testes: análise de ações da B3 e dos EUA, teste de estratégias com dados do passado e documentos da CVM e da SEC, cada número explicado. Python, Pandas, Streamlit e PostgreSQL.

Self-hosted multi-tenant Web Application Firewall + CDN platform (ModSecurity/OWASP CRS, FastAPI, React, ML-assisted rules)

AI-powered image classification application that identifies clothing, footwear, and accessory products using MobileNetV2 and TensorFlow.

Machine Learning Personalized Handwritten Digit Recognition from Minimal Data

Do you need an LLM? Classifying 342,000 Italian public tenders with classic ML, embeddings and LLMs on Amazon Bedrock.

🌊 End-to-end ML pipeline demonstrating explicit DAG orchestration (Prefect), strict data quality gates (Pandera), and automated lineage tracking (MLflow).

End-to-end Machine Learning solution for Heavy Equipment Price Prediction (IIT Madras BS MLP course). Features leak-free 5-fold CV, M-estimate target encoding, and LightGBM + CatBoost ensemble, achieving 0.18732 RMSLE on Kaggle.

Statistical analysis, hypothesis testing and machine learning on 1,000,000 Iranian real-estate listings — with an interactive dashboard

Smart Health Monitoring and Prediction System Using Machine Learning

Core ML model packages for typed AI decisions with OpenJevSwift on iOS and macOS (iPhone and Mac).

Bangalore house price prediction using a ridge regression model, with a Flask API and a static web UI

A multimodal document RAG pipeline that extracts and validates information from messy PDFs, scanned documents, and tables using OCR, LLMs, and a human review workflow.

Group Project for ISM6642 ML for Business Apps Course at Florida International University

Diamond price estimation, price-tier screening and five-grade cut diagnostics with 23 models, group-aware validation and auditable evaluation evidence.

Atividade de oficina de inteligência artificial, com o objetivo inicial que consiste na importação de bibliotecas, leitura e exploração descritiva de um conjunto de dados de desempenho acadêmico com 10.000 registros para diagnóstico prévio de ausências e duplicatas.

An educational repository featuring three notebooks for exploring machine learning applications using e-commerce data: demand forecasting, repurchase prediction, and customer segmentation