# 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.

## 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.

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.

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`.

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.

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](https://docs.datasaur.ai/assisted-labeling/predictive-labeling).