LibAUC: A Deep Learning Library for X-Risk Optimization
-
Updated
May 23, 2026 - Python
LibAUC: A Deep Learning Library for X-Risk Optimization
Top1 Solution on OGB Challenge (Graph Property Prediction on HIV dataset)
Introduction to Machine Learning with Python
This repository hosts a cutting-edge deep learning model developed to predict 6-month incident heart failure utilizing electronic health records (EHRs). Heart failure is a multifaceted medical condition characterized by its significant impact on patients' well-being and healthcare systems.
Hi all! My project aims to predict customer conversion for an insurance company. The main objective of the project is to develop an accurate and efficient model that can aid the insurance company in improving its sales conversion rate and reducing marketing costs.
CheXpert-based chest X-ray multi-label classification PoC with DenseNet121, AUROC/AUPRC evaluation, threshold tuning, and Grad-CAM visualization.
Developed a Logistic Regression model to detect anemia in patients by analyzing and refining data sets for improved accuracy.
mlopspl 🛠️🔄🚀 : E2E MLOps Vertex AI Pipelines # ML workflow # Kubeflow Pipelines SDK # Cloud Scheduler
This project implements a Machine Learning model that predicts if a college basketball player will be drafted to join the NBA League based on the player's statistics for the current season.
Classification prediction model
Cross-validation, knn classif, knn régression, svm à noyau, Ridge à noyau
Predicted rider retention for a taxi service and identified most significant factors that contributed to it. Achieved an 80% accuracy with a catboost model, which was chosen for its interpretability.
Snake — SAT-based explainable classifier. Shannon MI feature selection, 30 boolean test types, 7 oppose profiles. Auditable regression engine. Zero dependencies. Pure Python.
Add a description, image, and links to the auroc topic page so that developers can more easily learn about it.
To associate your repository with the auroc topic, visit your repo's landing page and select "manage topics."