h2oai/h2o-3

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

7494 stars · 2025 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

H2O-3 is an open-source, distributed, in-memory machine learning platform implementing algorithms such as GLM, GBM/XGBoost, Random Forest, Deep Learning, Stacked Ensembles, and AutoML. It is accessible from Python, R, Scala, Java, and a Flow web UI, integrates with Hadoop and Spark, and exports models as POJO/MOJO for fast production scoring.

Use cases

• train gradient boosting models on large datasets
• run automatic machine learning to find the best model
• train deep learning models from Python or R
• score models in production with MOJO export
• run machine learning on Hadoop or Spark clusters
• build stacked ensembles of multiple models
• do PCA, K-Means, and GLM on big data

When to choose

• you need distributed, scalable ML beyond a single machine's memory
• you want AutoML to automatically train and tune many models
• you need fast production scoring via POJO/MOJO export
• you work in Python or R but need big-data performance
• you want an Apache-licensed ML platform with Hadoop/Spark integration

When to avoid

• you need lightweight scikit-learn-style ML on small datasets
• you need deep learning with GPU training on neural architectures like CNNs or transformers
• you want a pure-Python stack without a JVM dependency
• you need LLM fine-tuning or generative AI features

Facets

library · maturity stable

machine-learning deep-learning data-science benchmarking machine-learning data-science big-data artificial-intelligence python jvm cross-platform cloud automl gbm gradient-boosting random-forest glm stacked-ensembles distributed-ml hadoop spark mojo-scoring r scala docker

Member repositories

For agents

markdown · JSON · MCP: product_card(name="h2oai/h2o-3")