A saved model can be deployed into a Dataiku DSS API node to query a prediction on new data.
The API node provides all the necessary features for scoring in production:
- See the deployment to real-time scoring tutorial to create your first API scoring service and deploy to an API node.
- High availability and scalability for scoring new records.
- Model versioning and rollback using model packages.
- The ability to score in realtime, even with models trained using a distributed engine.
- Scoring multiple models for A/B testing.
- And more advanced capacities such as enriching queries in real-time or handling custom Python models and custom R models.