Stacking
A Python library for stacked generalization (ensemble learning) that supports scikit-learn, XGBoost, and Keras models with out-of-fold prediction saving.
What is Stacking?
Stacking is a Python library that implements stacked generalization, an ensemble learning technique where predictions from multiple base models are combined using a meta-model to reduce generalization error. It solves the problem of building robust predictive systems by leveraging diverse algorithms while providing tools to save and analyze intermediate predictions.
Data scientists and machine learning engineers working on classification or regression tasks who want to implement ensemble methods beyond simple averaging or voting.
Developers choose Stacking for its clean API, support for popular ML frameworks, and unique ability to persist out-of-fold predictions—enabling deeper analysis and flexible multi-stage stacking workflows not easily available in other libraries.
Overview
Stacked Generalization (Ensemble Learning)
Use Cases
Best For
- Improving competition scores in Kaggle-style machine learning challenges
- Building robust predictive systems by combining diverse model types
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.
