Supported Amazon SageMaker models
Learn more about the Amazon SageMaker models to which you can connect in Prediction Studio.
Supported Amazon SageMaker models
You can connect to Amazon SageMaker models that use the following algorithms:
- TensorFlow
- XGBoost
- K-means
- K-nearest neighbors
- Linear learner
- Random cut forest
You can also connect to an Amazon SageMaker model that uses a custom algorithm. To connect to a custom model, configure the Amazon SageMaker docker container. For more information, see the Amazon Web Services documentation.
Supported input and output formats for Amazon SageMaker models
The supported input and output formats depend on the model algorithm. Consult the following table to learn more about the supported input and output formats for supported models:
Supported input and output formats for Amazon SageMaker models
| Model algorithm | Supported input format | Supported output format |
| TensorFlow | CSV | CSV |
| XGBoost | CSV | JSON |
| K-means | CSV | JSON |
| K-nearest neighbors | CSV | JSON |
| Linear learner | CSV | JSON |
| Random cut forest | CSV | JSON |
Previous topic Metadata file specification for predictive models Next topic Supported Google AI Platform models