A new page appears where you can optionally configure all the settings for the synthetization job. At this point, there’s also the possibility to start this job immediately.

To do so, click on Start this job in the upper right-hand corner of the screen. You can then skip the remaining data catalog configuration steps and continue with the Using data catalogs to generate synthetic databases guide.

Configure Run Data

The synthetization settings are organized by the following tabs:

Settings

Here you can specify the number of training and generated subjects.

Relationships

Here you can link your tables by specifying their primary and foreign key.

Table details

Here you can review the encoding types that MOSTLY AI assigned and configure column-specific training and synthetization parameters.

Above these tabs, there’s a field where you can fill out the name of your data catalog. This name will help you locate this data catalog when you want to use it to start a synthetization job, or when you want to return to it to adjust the settings. It won’t be present in the synthetic dataset.

Configure Run Data

In the next step, we’ll dive into the settings and configure your synthetization job.