XGBoost© is an advanced implementation of a gradient boosting algorithm. Boosting algorithms iteratively learn weak classifiers and then add them to a final strong classifier. XGBoost is very flexible and provides many parameters that can be overwhelming to most users, so the XGBoost-AS node in Watson Studio exposes the core features and commonly used parameters. The XGBoost-AS node is implemented in Spark.
For more information about boosting algorithms, see the XGBoost Tutorials. 1
Note that the XGBoost cross-validation function is not supported in Watson Studio. You can use the Partition node for this functionality. Also note that XGBoost in Watson Studio performs one-hot encoding automatically for categorical variables.
- On Mac, version 10.12.3 or higher is required for building XGBoost-AS models.
- XGBoost isn't supported on IBM POWER.
1 "XGBoost Tutorials." Scalable and Flexible Gradient Boosting. Web. © 2015-2016 DMLC.