open-solution-home-credit
An open-source machine learning solution for the Home Credit Default Risk Kaggle competition, providing reproducible code and experiments.
What is open-solution-home-credit?
neptune-ml/open-solution-home-credit is an open-source solution to the Home Credit Default Risk Kaggle competition, which focuses on predicting loan default risk. It provides clean, reproducible code for building machine learning models, including feature engineering and hyperparameter tuning, to serve as a benchmark and educational resource. The project emphasizes transparency and collaborative improvement through documented iterative solutions and experiment tracking.
Data scientists and Kaggle competitors, especially those new to the Home Credit Default Risk competition or seeking to learn from structured, reproducible machine learning workflows. It is also suitable for developers interested in experiment tracking with Neptune.ml and collaborative open-source data science projects.
Developers choose this project because it offers a ready-to-use, well-documented benchmark with multiple solution branches (e.g., LightGBM, XGBoost, stacking) that demonstrate progressive improvements. Its integration with Neptune.ml for experiment tracking provides live previews of experiments, though it remains optional, allowing flexibility for users who prefer plain Python scripts.
Overview
Open solution to the Home Credit Default Risk challenge :house_with_garden:
Use Cases
Best For
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
