Skip to main content Skip to complementary content

Tutorial – Generating and visualizing prediction data

This tutorial teaches you how to use Qlik AutoML to train and deploy a machine learning model for making predictions. It also teaches you how you can visualize the prediction data in a Qlik Sense app.

We will consider the scenario of customer churn, a classic example of a binary classification problem. The goal is to be able to reliably predict whether a customer will cancel their subscription or remain a subscriber to a service. There are only two outcomes in this type of problem: true or false (churned, or not churned).

To approach this machine learning problem, we will start by processing a set of data for which we already know the outcome, then apply statistical modeling created from that data to new data we would like to predict the outcomes for.

You will begin this tutorial by creating an experiment. From there, you will train models and deploy one of them into an ML deployment. This ML deployment will be used to create predictions, which can be visualized in a Qlik Sense app.

What you will learn

Once you have completed this tutorial, you will understand the different steps involved in creating and configuring an experiment. You will also learn how to interpret model scores. Finally, you will be able to deploy a machine learning model and will understand how your predictions data can be used to generate compelling Qlik Sense visualizations in Qlik Cloud Analytics.

This tutorial shows you how to manually iterate your models by identifying common issues with your dataset and training results. By default, Qlik AutoML trains your models with intelligent model optimization. With intelligent optimization, problematic features are removed automatically from model training. This increases the likelihood that your models will be ready to deploy after a single version with minimal further iteration needed. For an example showing how to train models with intelligent optimization, see Example – Training models with automated machine learning.

Who should complete this tutorial

This tutorial is designed for users who want an introduction to automated machine learning and data visualization in Qlik Cloud Analytics. Some basic knowledge of machine learning and Qlik Sense is helpful, but not required.

To complete this tutorial, you need the following:

If you are not able to view or create ML resources, this likely means that you do not have the required roles, entitlements, or permissions. Contact your tenant admin for further information.

For more information, see Who can work with Qlik AutoML.

What you need to do before you start

First, you need to download the tutorial materials linked below. Choose between the CSV and QVD workflows. Downloading the pre-configured app is optional.

When you have downloaded your desired materials, unzip them on your desktop.

  • AutoMLTutorialDatasetsCSV

    : Contains tutorial data in CSV format. This option is easier for getting started quickly.

  • AutoMLTutorialDatasetsQVF: Contains tutorial data in the format of .qvf scripts that can be run to create QVDs. This option takes a bit longer than CSV but is helpful in introducing you to working with Qlik data formats and scripting.

  • AutoMLTutorialPreConfiguredApp: This item is optional. It is a sample copy of the Qlik Sense app that you will build during the tutorial. This allows you to skip past the training and deployment stages for quicker hands-on experience with predictive app development. For more information, see Alternative workflow: Upload pre-configured app.

AutoML tutorial

The training dataset contains information about customers whose deadline for renewal has passed, and have made the decision to churn or remain subscribed to the service.

The apply dataset contains details about a new set of customers whose renewal date has not yet passed. It has not yet been determined whether or not these customers will cancel their service. The goal, with this tutorial, is to predict what this set of customers will do, with the hope that we can decrease the likelihood that they will churn.

Option 1: AutoML tutorial datasets (CSV)

  1. Open the Qlik Cloud Analytics hub.

  2. Click Add new > Dataset, and then select Upload data file.

    If you are using the new platform navigation experience, go to the Create page, select Dataset, and then select Upload data file.

  3. Drag the AutoML Tutorial - Churn data - training.csv file to the upload dialog.

  4. Next, drag the AutoML Tutorial - Churn data - apply.csv file to the upload dialog.

  5. Select a space. It can be your personal space or a shared space if you want other users to be able to access this data.

  6. Click Upload.

Now that your datasets are uploaded, you can proceed to creating an experiment.

Option 2: AutoML tutorial datasets (QVD)

  1. Open the Qlik Cloud Analytics hub.

  2. Click Add new > Upload, and then select Script.

    If you are using the new platform navigation experience, go to the Create page, select Upload, and then select Script.

  3. Drag these files to the upload dialog:

    • AutoML Tutorial - Churn data - training.qvf

    • AutoML Tutorial - Churn data - apply.qvf

  4. Select a space. It can be your personal space or a shared space if you want other users to be able to access this data.

  5. Click Upload.

  6. For each uploaded script, do the following:

    1. Open the script and switch to the Editor tab.

    2. In Editor, Click Export data.

    The QVD dataset is created in the same space where you uploaded the script.

Now that your datasets are created, you can proceed to creating an experiment.

Lessons in this tutorial

The topics in this tutorial are designed to be completed in sequence. However, you can step away and return at any time.

Further reading and resources

Your opinion matters

We appreciate any feedback that you may have. Please use the section below to let us know how we're doing.

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!