Predictive Churn

Predictive churn analyzes your audience for users that exhibit behaviors indicating they are likely to become inactive, and tags the users as High, Medium, or Low risk. Use predictive churn to identify users who are likely to leave your App or Web channels, and take steps to retain them.

Churn is a natural part of engagement ebb and flow, and while a certain amount of churn is normal and healthy, there are ways to identify churn risk factors and take actions to prevent your user base from eroding.

With predictive churn, you can identify users by their likelihood to churn, based on risk profiles that we generate via machine learning, using gradient boosted decision tree methodology. Our churn prediction model is trained to detect the most relevant risk factors for a churn outcome, and assigns either a high, medium, or low churn factor to each user who has been active in the past 60 days.

Risk factors update weekly and are exposed as TagsMetadata that you can associate with channels or Named Users for audience segmentation. Generally, they are descriptive terms indicating user preferences or other categorizations, e.g., wine_enthusiast or weather_alerts_los_angeles. Tags are case-sensitive. for segmentation and analysis in Performance AnalyticsA customizable marketing intelligence tool that provides access to reports and graphs based on engagement data., and exposed as Tag Change events in Real-Time Data StreamingA service that delivers engagement events in real time via the Data Streaming API or an Airship partner integration..

You can also target your audience by risk profile or use changes in churn risk as a trigger for an automation or sequence.

You can enable predictive churn for your app and web audiences. Both are tracked and reported independently.

The Predictive Churn Model

Predictive churn belongs to Airship’s Predictive suite of products, which uses machine learning to predict user behaviors and optimize engagement strategy for customer lifecycle marketers.

The predictive churn model is trained on recency and frequency of notification sends and app opens or website visits for a cross-section of anonymized apps and sites. By including your app key as an input, the model tailors its predictions to your audience based on your app or website’s feature usage — recency, frequency, etc.

Active User

An active user is a member of your audience that has opened your app, had an active web session, or clicked a web notification in the last 30 days.

Inactive User

An inactive user is a member of your audience that had a predictive tag of high, medium, or low and has not opened your app, had an active web session, or clicked a web notification in the last 30 days.

Churn

A churn outcome occurs when a previously active user becomes inactive, i.e., Airship has not seen any activity (measured in app opens, website visits, or web notification clicks) from a user in the last 30 days. Push opt-in status does not factor into the churn outcome, so it is possible that a user who opted out of notifications could still appear active for churn prediction purposes.

Note

A churned user is not the same as an uninstalled user.

Churn Risk

Predictive churn makes a prediction about the likelihood of a future churn outcome, meaning that a user will go inactive. We assign one of three measures of risk for such an outcome:

High — Users most likely to become inactive
Medium — Users who exhibit signs of potentially becoming inactive
Low — Users least likely to become inactive

Predictive Churn Use Cases

Target users with offers before they churn.
Run an A/B Test with a single variant and a control group to measure the message’s impact on churn.
Trigger an automation or sequence based on a change in risk group.
Send a message in a sequence based on a change in risk group.
Create a SegmentA grouping of audience members selected by unique or shared identifiers. Multiple identifiers can be combined within a Segment. that blends risk groups based on the type of messaging and your goals.

Predictive Churn in the API

In the Airship API, predictive churn is represented as a tag group applied to app or web channels — depending on whether you enable Predictive App Churn, Predictive Web Churn, or both. You can use the ua_churn_prediction tag group to target high, medium or low risk members of your audience.

Predictive Churn Data and Analytics

If you are a Performance AnalyticsA customizable marketing intelligence tool that provides access to reports and graphs based on engagement data. customer, the Predictive Dashboard helps you track churn risk factors over time. The Predictive Dashboard provides a view into Predictive Churn risk groups, distribution of users across risk groups, and the performance of churn mitigation tactics. If you have both Predictive App and Web Churn enabled, you can set the Device Family filter to Web or Mobile to see churn data for either audience.

Predictive tags update every Sunday, and reports default to the most recent update.

Use Cases

Explore added or removed Predictive tags.
Slice user behavior by churn risk tag.
Export ad IDs, named users, and channel IDs based on their risk category.
Export named users and ad IDs based on app opens, uninstalls, and risk category.
Find churn cohorts and slice by the users’ current tags.
Find churn cohorts, filter, then analyze a funnel of past behavior.

Predictive Churn Events

Predictive churn is represented as a tag applied to a channel. Therefore, changes in predictive churn status are represented as TAG_CHANGE events in Real-Time Data Streaming.

Enable Predictive Churn

Predictive churn supports production projects only and updates weekly on Mondays. Tags are assigned the first Monday after enabling predictive churn. Predictive App and Web Churn are independent settings. If your app and website both use the Airship SDK, you should turn both settings on.

Go to Settings » Project configuration and click Manage for Predictive AI.
Enable Predictive App Churn and/or Predictive Web Churn.

Automate Messages by Predictive Churn Group

Automation is a set of conditions that your audience must meet before they receive a message. You can trigger automation or a SequenceA series of messages that is initiated by a trigger. Airship sends messages in the series based on your timing settings, and you can also set conditions that determine its audience and continuation. Sequences can be connected to each other and to other messaging components to create continuous user experiences in a Journey. based on changes to a user’s predictive churn status. For example, you might set up an automation to send users a special offer when their predictive churn risk changes to High, helping retain users at risk of leaving your audience.

In the Setup step of an automation or Trigger step in a sequence:

Select the Predicted to Churn trigger.
Select a risk profile.
- High risk: Users most likely to become inactive.
- Medium risk: Users who exhibit signs of potentially becoming inactive.
- Low risk: Users least likely to become inactive.
Choose whether to apply the trigger when the risk is added or removed.

Send a Message to a Predictive Churn Audience

In the Audience step of the Message or A/B Test composers:

Select the channels to include in your audience.
Select Target Specific Users.
Search for and select Predicted to Churn, then select High risk, Medium risk, or Low risk.

Send an In-App Automation to a Predictive Churn Audience

In the Audience step of the In-App Automation composer:

Select Target Specific Users.
Click the Predicted to Churn trigger.
Select a risk group.
- High risk: Users most likely to become inactive.
- Medium risk: Users who exhibit signs of potentially becoming inactive.
- Low risk: Users least likely to become inactive.

Select a Predictive Churn Audience Using the API

Predictive Churn is represented as a tag group called ua_churn_prediction, with tags for low, medium, and high risk. You can use the audience tag selector to target an audience at risk of churning.

For example, the following is a notification to users of all device types whose current churn prediction is medium:

POST /api/push HTTP/1.1
Authorization: Basic <master authorization string>
Content-Type: application/json
Accept: application/vnd.urbanairship+json; version=3

{
   "audience": {
      "tag": "medium",
      "group": "ua_churn_prediction"
   },
   "notification": {
        "alert": "me·di·um, n., an agency or means of doing something."
    },
    "device_types": [
       "ios",
       "android",
       "web"
    ]
}

Include a Predictive Churn Risk Group in an Audience Segment

You can include a predictive churn risk profile in your SegmentsA grouping of audience members selected by unique or shared identifiers. Multiple identifiers can be combined within a Segment..

Follow the steps in the Segment Builder Tutorial to create a new segment, and include a Predicted to Churn status:

Search for and select Predicted to Churn.
Select High risk, Medium risk, or Low risk.

Observe Churn Prediction in Performance Analytics

See the Predictive information in Performance Analytics Dashboard and Look definitions.

Predictive Churn Events

Predictive Churn is a tag applied to users. Therefore, changes in predictive churn status are represented as TAG_CHANGE events. See the Data Streaming API Reference for details on Real-Time Data StreamingA service that delivers engagement events in real time via the Data Streaming API or an Airship partner integration. tag change events.

Tag changes return both the change in tag — add or remove — and the current tag. The current tag is the end result of the tag change. There are three scenarios for tag change events:

Add prediction: Adds a new predictive churn tag to a channel that did not previously have a prediction. Not all devices begin with a churn prediction; churn prediction is assigned to active users when the predictive churn model runs (weekly on Mondays).
Prediction change: Replaces the prediction on a channel.
Remove prediction: Removes the prediction from a channel, typically when a channel becomes inactive.

The following is an example change in churn prediction status:

{
   "id": "e1559cd7-af96-45ab-bb74-a22cd99a01d5",
   "offset": "1422600",
   "occurred": "2017-01-15T09:26:30.362Z",
   "processed": "2017-01-15T16:15:30.048Z",
   "device": {
      "android_channel": "d5ec96e3-5ced-47b0-a4dd-1b2b6bda442e",
      "named_user_id": "job.bob@example.com",
      "attributes": {
         "locale_variant": "",
         "app_version": "312",
         "device_model": "LG-H811",
         "connection_type": "WIFI",
         "app_package_name": "com.company.app",
         "iana_timezone": "America/Los_Angeles",
         "push_opt_in": "true",
         "locale_country_code": "US",
         "device_os": "6.0",
         "locale_timezone": "-28800",
         "carrier": "T-Mobile",
         "locale_language_code": "en",
         "location_enabled": "true",
         "background_push_enabled": "true",
         "ua_sdk_version": "6.1.2",
         "location_permission": "ALWAYS_ALLOWED"
      }
   },
   "body": {
      "add": {
         "ua_churn_prediction": [
         "medium"
         ]
      },
      "remove": {
         "ua_churn_prediction": [
         "high"
         ]
      },
      "current": {
         "ua_churn_prediction": [
         "medium"
         ]
      }
   },
   "type": "TAG_CHANGE"
   }

Feedback

Was this page helpful?