> For the complete documentation index, see [llms.txt](https://docs.datasaur.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.datasaur.ai/advanced/extensions/predictive-labeling.md).

# Predictive Labeling

## Overview

**Predictive labeling** uses machine learning to generate labels based on a subset of manually labeled data. It helps reduce manual labeling effort and improves consistency, especially for large datasets.

<figure><img src="/files/8v0t8NqjAKKFcVMaSlN9" alt=""><figcaption></figcaption></figure>

## Use case

This example uses **Predictive labeling** for spam message detection.

1. Create a [row labeling](/data-studio-projects/creating-a-project.md) project.

   <figure><img src="/files/Mip2WMtp0zqPUEhNQGJe" alt=""><figcaption></figcaption></figure>
2. Click the gear icon from the extension panel on the right to open the **Manage extensions** dialog, then enable the **Predictive labeling** extension.

   <figure><img src="/files/Ia8uxwKZ0TtPG51PkNFD" alt=""><figcaption></figcaption></figure>
3. Label at least five items for each answer option. For example, if you have two answer options (`True` and `False`), label at least five items as `True` and five items as `False`.
4. Select the input columns as context for the prediction and select the target field where predicted labels will be added. Then click **Save configuration**.

   <figure><img src="/files/V20snq4EzGbfIaSvNC0d" alt=""><figcaption></figcaption></figure>
5. Review the predicted labels and choose **Accept** or **Reject**.

   <figure><img src="/files/UIRNrpgws67sL0TlIfBn" alt=""><figcaption></figcaption></figure>

{% hint style="info" %}
For further details, please visit [Assisted Labeling - Predictive Labeling](/assisted-labeling/predictive-labeling.md).
{% endhint %}