Explore projects

Data Science / Machine Learning Pipeline component for training and deploying ML models using CI

A project providing digital recognition of handwritten documents using machine learning techniques.

Quantum Machine Learning

Somewhat intuitive interface for data science and machine learning algorithms

learning machine learning

Miscellaneous machine learning capabilities.

Deploy do projeto de TCC do MBA Machine Learning in Production. Kafka para a mensageria em Minikube.

Pipeline that simulates deformations of synthetic (or real) bodies for machine learning problems

A project providing digital recognition of handwritten documents using machine learning techniques.

Python utilities for converting machine learning (ML) models from their custom formats into formats ensuring long-term stability, i.e. vanilla Python, vanilla C++ or ONNX, so they can be safely used forever without risk of framework breaking-changes. Supported are

sklearn, TMVA and MVAUtils boosted decision trees (for classification or regression) TMVA MLPs and lightweightNNs

Open Labeller for Iterative Machine learning

En los últimos años ha habido un incremento en la implementación de técnicas de Machine Learning aplicadas a diferentes tópicos tanto dentro como fuera del mundo empresarial. En este trabajo se propone aplicar y evaluar tres técnicas de Sentiment Analysis a reviews en español de productos de Mercado Libre. Se intentará buscar modelos óptimos de Naive Bayes, Support Vector Machine y Long-Short Term Memory. También se experimentó con datasets reales de reviews positivas y negativas escritas por humanos, se crearon modelos y se los compararon entre si. Se ha encontrado las diferencias entre estos, y como se comparan al analizar reviews neutrales.

A project providing digital recognition of handwritten documents using machine learning techniques.

Machine Learning Mini-Project made using Python by Batuhan Basoglu, Jared Tritt, Shaani Bellemare

A production-oriented Machine Learning pipeline that predicts whether an active user session will result in a purchase.

Model: XGBoost Classifier optimized for class imbalance.

Performance: ROC AUC 0.936 | F1-score 0.71 (at 0.30 threshold).

Key Features: Reproducible environment (uv), modular CLI for training/inference, leakage-free preprocessing, and SHAP interpretability analysis.

Data: UCI Online Shoppers Purchasing Intention Dataset.

Tech Stack: Python, XGBoost, Scikit-learn, Pandas, SHAP.

Lecture material for machine learning applied to computational fluid mechanics