XGBoost

Health v2 · maintenance only

Adoption not part of the score

28887 stars · 8947 forks observed · 2026-10-19

What it is AI-extracted, prompt v1, taxonomy v1, 2026-10-05, confidence 0.99

XGBoost is an optimized, scalable gradient boosting library written in C++ with bindings for Python, R, Java, Scala and other languages. It supports single‑machine and distributed training on platforms such as Hadoop, Spark, Dask and Kubernetes.

Use cases

• train high‑performance gradient boosting models on large tabular datasets
• run distributed model training across a Spark or Dask cluster
• perform feature importance analysis and model interpretation for tree ensembles
• apply XGBoost for ranking tasks in information retrieval
• use GPU acceleration to speed up training on massive data

When to choose

• you need a fast, memory‑efficient implementation of gradient boosting
• your workload requires scaling to billions of examples or distributed training
• you want seamless integration with Python, R, Java, or Scala ecosystems
• GPU support is important for reducing training time

When to avoid

• you need deep learning models such as neural networks
• your data is primarily unstructured text or images requiring convolutional architectures
• you prefer a pure Python library with minimal compiled dependencies

Facets

library · maturity active

machine-learning machine-learning data-science windows python jvm cpp gradient-boosting gbdt distributed xgboost tree-ensemble linux macos r

Member repositories

For agents

markdown · JSON · MCP: product_card(name="dmlc/xgboost")