Engagement and Churn Score

Engagement and Churn Score
Use Cases
Determine users at risk of churn, star users and regular users


Before you reach this stage, ensure you’ve:
  1. Created a schema
  1. Integrated code to process your data and installed Begin’s Unity SDK
  1. Created a project with the objective “Engagement & Churn Score”
Learning usually takes about 30 minutes. Once complete, your machine learning algorithm is ready to be used on your mobile device, browser, connected vehicles, or server applications.


In order to get engagement scores, follow the initialization step:
using BeginAI; BeginWorker worker = BeginWorker.GetInstance(APP_ID, LICENSE_KEY);
To use your trained algorithm, input the following code:
This will return a dictionary with data in the following format:
  • avg_bottom_10_slope: Average bottom 10 slope for the given project’s target object in the date range
  • avg_top_10_slope: Average top 10 slope for the given project’s target object in the date range
  • ranked_slope: String ranked slope score, as a percentage
  • slope: Slope score as a floating point number
  • classification: Slowly Disengaging, Dropping Off, Rising Star or Stable based on the behaviour analysis
In case the provided target object id doesn’t exist, the string NOT_FOUND will be returned
If you performed the initial processing in Unity, you can still use the algorithm with other SDKs like Python or JavaScript SDKs.
Note: Begin’s algorithms can learn continuously with additional user data while your code is deployed. Your project can learn from datasets on your mobile application, server or other applications without you having to worry about merging the learning or merging the data. Begin will take care of merging the learning.