Creating experiments

You can create new experiments in personal spaces or shared spaces for collaboration.

Requirements and permissions

To learn more about the user requirements for working with ML experiments, see Working with experiments.

Creating experiments

You create experiments from the Analytics activity center.

Do the following:

1. Go to the Create page of the Analytics activity center and select ML experiment.

   Alternatively, go to Predict and select ML experiment. Alternatively, in Catalog, click Create new > ML experiment.

2. Enter a name and space, and, optionally, a description and tags.

3. Click Create.

   The Open experiment checkbox is selected by default. If you deselect this checkbox, you must open the experiment manually before proceeding to the next step.

4. Select a dataset to use in your experiment. You can choose from all supported datasets that are available in your private and shared spaces.

   Datasets can be uploaded via the Create page in the Analytics activity center, and are visible in Catalog. You can also upload a new dataset directly into Catalog from the experiment's dataset selection page. This dataset will then automatically be selected as the training dataset for use in your experiment. To do so, click Add training dataset and choose the file to upload.

   Information note

   Any flat file that can be uploaded and profiled in Qlik Cloud is supported for use in Qlik AutoML.

   For multi-table files such as Microsoft Excel files with multiple sheets, only the first table will be imported. If data profiling fails for a table (for example, if it is empty), the file is not supported.

The next step in the process is to configure the experiment. See Configuring experiments.

Editing experiment name and other details

Do the following:

1. Click by the experiment name.

2. Edit the name or other details.

Deleting experiments

You can delete an experiment from Catalog.