Skip to main content Skip to complementary content

Introducing automated machine learning

Automate machine learning for your analytics team with Qlik AutoML. With the simple code-free interface, you can easily create machine learning experiments to generate models and make predictions.

What is machine learning

Machine learning is a branch of artificial intelligence and data science focused on recognizing patterns in historical data to predict future outcomes. Algorithms are trained on the data to build a predictive model without being explicitly programmed to do so. A machine learning model can help you answer questions like:

  • Will a gym customer cancel their membership?

  • What is the expected lifetime value for a given customer?

Read more about the basic concepts in Understanding machine learning. You will also learn about the structured framework for defining machine learning questions and preparing datasets.

What can you do with automated machine learning

Create automated machine learning experiments in Qlik Sense. In the hub, you can collaborate on the experiment with other users and easily load data from Catalog to train the model.

Integrate your predictive analytics with Qlik Sense apps to share your findings. Explore further with visualizations and interactive what-if scenarios to understand how changing different parameters might affect your desired outcome.

You can make predictions for datasets stored in Catalog or make operational predictions in real-time using Qlik Sense APIs.

How do experiments work

An experiment trains machine learning algorithms on a particular dataset with a particular target. The training generates machine learning models, which you can use to make predictions.

Most of the process is automated in automated machine learning. When you create an experiment and load a dataset, the dataset is automatically analyzed and the data is preprocessed to make it ready for machine learning. Statistics and other information about each column are displayed to help you select a target. When you start the training, several algorithms start searching for patterns in the data. For more information about creating and training experiments, see Working with experiments.

When the training is finished, scores and ranks let you evaluate the generated machine learning models. By changing parameters and iterating the training, you can generate a number of versions. Choose the best-performing model for your dataset and deploy it to start making predictions. For more information, see Working with ML deployments.

As the following image shows, an experiment can have multiple versions, each using one or more algorithms. The model with the best performing algorithm can be deployed to make predictions. This means that one experiment can result in several ML deployments.

Overview of how experiments, versions, algorithms, models, and predictions are related.

Who can work with experiments and ML deployments

Users with Professional or Full User entitlement can create experiments in personal or shared spaces in Qlik Cloud. They can deploy models in personal or shared spaces and generate predictions. They can also publish ML deployments to managed spaces.

Your experiments and ML deployments are stored in Catalog. Filter by type or use the collections to find them easily. Access is controlled through the space. For more information about spaces, see Working in spaces.

Tenant admins can manage experiments and ML deployments from the Management Console. For more information, see Managing experiments and ML deployments.

AutoML limitations and license-governed capacities

AutoML is an additional paid-for capability. Some limited functionality is included in applicable subscriptions. The specific capabilities and capacity are dependent on your subscription tier.


  • Maximum number of columns in the dataset: 500

    This applies to the datasets used for training experiments and generating predictions. The limit is the number of columns used as features in an experiment version. More columns can be in the dataset and limits are calculated when columns are included in the dataset.

License-governed capacities

Your customer license determines the capacity of various metrics governing how you can use Qlik AutoML. There are multiple tiers of AutoML available, depending on your business needs. There are the following two types of tiers:

  • Included tier: This is the basic AutoML functionality with limited capabilities. It is included with a subscription to Qlik Sense Enterprise SaaS, Qlik Cloud Analytics Premium, Qlik Cloud Enterprise, or Qlik Cloud Data Integration (Standard or Premium). The included tier is suitable for trial purposes, and for evaluating how Qlik AutoML can help meet your business needs. It is not suitable for production use cases. For more comprehensive capabilities, consider a paid tier of Qlik AutoML.

  • Paid tiers: There are a number of packages providing the comprehensive AutoML capacities needed for production use cases. They are available as additional paid add-ons to a Qlik Cloud subscription.

Regardless of which tier you are using, Qlik AutoML has an API rate limit of 300 requests per minute.

The following features are only available in the paid tiers of Qlik AutoML:

  • Hyperparameter optimization

  • Scheduled predictions

  • Real-time predictions

  • Qlik AutoML connector

For more information about what is included in each type of AutoML tier, see the table below.

Qlik AutoML metrics and availability by tier type
Metric Description Available in included tier Available in paid tiers
Deployed models The tier included in a Qlik Cloud subscription defines a maximum number of deployed models that can be created across all tenants created within the license. This consumption limit is defined per model, meaning that multiple ML deployments created from a single model count as a single deployed model. Yes Yes
Concurrent training This is the number of models a tenant can train in parallel. In the included tier of Qlik AutoML, each model will be run one after another. Paid tiers include capacity allowing your tenant to train multiple models simultaneously. No Yes
Increased dataset size Paid tiers provide for increased dataset sizes for training models. No Yes
Manual batch predictions Predict all rows in a dataset manually. Yes Yes
Scheduled batch predictions Configure your predictions to run on a schedule, rather than initiating them manually. Scheduled predictions are only available with paid tiers of Qlik AutoML. For more information, see Scheduling predictions. No Yes
Real-time predictions Employ this API to use your ML deployments to run predictions in real time. For more information, see Creating real-time predictions. No Yes
Qlik AutoML connector in Qlik Cloud Analytics With this analytics connector, you can load data from the integrated Qlik AutoML platform into Qlik Cloud. For more information, see Qlik AutoML analytics source. No Yes
Hyperparameter optimization Hyperparameter optimization allows you to fine-tune your AutoML models for increased control over the learning process. For more information, see Hyperparameter optimization. No Yes
Information note The ML deployments you create in Qlik AutoML do not expire. If you have reached the maximum number of deployed models, delete one or more existing deployed models or upgrade your subscription to a higher tier.

For detailed information about your license metrics, see Product Description for Qlik Cloud® Subscriptions. Administrators can view license information and monitor the number of deployed models in the Management Console. For more information, see Monitoring resource consumption.

Learn more

Did this page help you?

If you find any issues with this page or its content – a typo, a missing step, or a technical error – let us know how we can improve!