How do I calibrate my model?

Kumo handles much of the model calibration behind-the-scenes automatically. For example, all outputs concerned with classification tasks are calibrated using Platt Scaling to ensure the prediction scores match with their actual probabilities of being true. Kumo 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 set various fine-tuning configurations to control the shape and structure of your model.

Learn More

• Platt Calibration of Classification Tasks
• Model Planner and AutoML