<!--
{
  "documentType" : "article",
  "framework" : "CoreML",
  "identifier" : "/documentation/CoreML/model-personalization",
  "metadataVersion" : "0.1.0",
  "role" : "collectionGroup",
  "title" : "Model Personalization"
}
-->

# Model Personalization

Update your model to adapt to new data.

## Discussion

On-device model updates provide your app the flexibility to personalize a user’s experience. For example, ordering a mocha at your favorite coffee shop every day increases a model’s ability to recommend that drink on subsequent visits. With the Core ML framework, you can adapt to incoming data with an updatable model at runtime on the user’s device.

## Topics

### On-device model updates

[`MLTask`](/documentation/CoreML/MLTask)

An abstract base class for machine learning tasks.

[Personalizing a Model with On-Device Updates](/documentation/CoreML/personalizing-a-model-with-on-device-updates)

Modify an updatable Core ML model by running an update task with labeled data.

[`MLUpdateTask`](/documentation/CoreML/MLUpdateTask)

A task that updates a model with additional training data.


---

Copyright &copy; 2026 Apple Inc. All rights reserved. | [Terms of Use](https://www.apple.com/legal/internet-services/terms/site.html) | [Privacy Policy](https://www.apple.com/privacy/privacy-policy)