Incorporate Predictive Churn Modeling from Kochava
Apple has introduced iOS 15 updates that will make uninstall tracking nearly impossible for iOS apps. With the recent push for privacy, it is no surprise that Apple is cracking down on this common tactic to detect uninstalled apps.
What is uninstall tracking and how does it work?
Uninstall tracking works by sending a “silent” push notification to a device. If the push notification fails at any point, it is assumed the app was uninstalled. By tracking uninstalls, marketers get valuable insights on user attrition. Marketers can also use this data to retarget lost users for reacquisition or suppress them in future acquisition targeting.
Employing Apple’s push notification system and using it for other purposes outside what is stated in their policy has been leniently enforced. However, with iOS 15, uninstall tracking will no longer be viable as part of an effort to ensure more security and privacy for app users.
Predictive churn modeling
While uninstall tracking will be unavailable come iOS 15, Kochava predictive churn modeling has been a tried and true method for forecasting user behavior. Whether you have utilized uninstall tracking in the past or need a way to decrease user drop-off, predictive churn modeling is available to increase your user’s lifetime value.
How it works
After a new app install, our machine learning algorithms go to work using a form of decision tree modeling to analyze recency, frequency, trend metrics, and other data variables during the first 7 days of a user’s interactions with the app.
On day 8, the user is assigned a churn score. “Churn” in this case means how likely is the device to not have activity in the app between day 8 and day 38 after install.
A user with a “Low” score indicates that it’s likely they will have further engagement with the app between day 8 and day 38. A user with a “High” score indicates that it’s likely they will churn/uninstall between day 8 and day 38.
Predictive churn modeling is a future-proof method of proactively identifying the likelihood a user will churn with 90% accuracy. With this tool, marketers can:
- Grow user engagement: View each individual churn score and target at-risk users with relevant push, SMS, or in-app messaging through owned media channels to increase users lifetime value (LTV).
- Segment audiences: Segment audiences based on their churn score and activate those audiences with effective reengagement campaigns to improve user retention.
- Create lookalike models: Users with low churn scores can be used as seed audiences to build lookalike models to attract quality users with similar characteristics that promote loyalty and retention.
- Assess partner quality: Break down your audiences by partner based on churn score and prioritize partners who deliver audiences with low churn likelihood to increase your return on investment (ROI).
Wouldn’t you want to know if a user will churn before they actually do? Uninstall tracking only tells you after the fact. Stay a step (or more) ahead with Kochava predictive churn modeling. Evaluate your user’s behavior to gain valuable insights into their future actions and produce marketing content to keep them engaged.