> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/sdgm/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/sdgm/_mcp/server.

# How do I calibrate my model?

> Understand automatic classification calibration and available model controls

> **Prerelease documentation**
>
> This Kumo Studio information is prerelease and is not yet supported. Stay tuned for the Docker and Kubernetes releases.

Kumo handles much of the model calibration automatically.
For example, all classification outputs are calibrated using Platt Scaling to ensure prediction scores reflect their actual probabilities.
Kumo also automatically refreshes underlying table and graph data when a model is trained, re-trained, or when a batch prediction is created.

If you need fine-grained control over the encoders, training strategy, or the AutoML search space, you can use Kumo's model planner to configure these settings.

### Learn More

* [Batch Prediction Outputs](/kumo-engine/1.0.0/kumo-studio-guide-coming-soon/preliminary-documentation/run-models/batch-prediction-outputs)
* [Evaluation](/kumo-engine/1.0.0/kumo-studio-guide-coming-soon/preliminary-documentation/train-model/evaluation/evaluation)
* [Model Planner and AutoML](/kumo-engine/1.0.0/kumo-studio-guide-coming-soon/preliminary-documentation/train-model/model-settings/model-planner)