# Predictive Labeling

## Overview

Datasaur's **Predictive labeling** utilizes machine learning to automate the labeling process by predicting labels for data based on a subset of manually labeled entries. This feature significantly reduces the time and effort required for manual data labeling, especially useful for large datasets. The **Predictive labeling** extension allows users to streamline their labeling workflow, enhance consistency, and achieve cost-effective data labeling process.

<figure><img src="/files/8v0t8NqjAKKFcVMaSlN9" alt=""><figcaption><p><strong>Predictive labeling</strong> extension</p></figcaption></figure>

## Use Case

Let's use **Predictive labeling** to annotate our spam message detection model.

1. Create a project: Follow the guide [here](https://docs.datasaur.ai/nlp-projects/creating-a-project) to create a row labeling project. Here’s what the data looks like.

   <figure><img src="/files/Mip2WMtp0zqPUEhNQGJe" alt=""><figcaption><p>Empty Row Based Project</p></figcaption></figure>
2. Enable **Predictive labeling**: 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><p>Manage Extension</p></figcaption></figure>
3. Manually label the data: Once it's enabled, you can start labeling your data. Make sure to label a minimum of five items for each answer category. For example, if you have two categories—`True` and `False`—label at least five items as `True` and five items as `False`.

   <figure><img src="/files/V20snq4EzGbfIaSvNC0d" alt=""><figcaption><p>Manual Labeling</p></figcaption></figure>
4. Predicting the labels: You can select the **Input column(s)** as the context, in this case, it will be **Message** and the **Target field** as the column for the predicted answer. Then, click **Save configuration**. Voilà, the **Predictive labeling** extension has automatically predicted all the labels.

   <figure><img src="/files/UIRNrpgws67sL0TlIfBn" alt=""><figcaption><p>Predict Labeling Result</p></figcaption></figure>
5. Review the results: You can now review the results, individually accept/reject them, or click **Accept all** or **Reject all**.

For further details, please visit the [Assisted Labeling - Predictive Labeling](/assisted-labeling/predictive-labeling.md).


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.datasaur.ai/advanced/extensions/predictive-labeling.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.