Use AI models to predict customer attrition and churn
We recently released a pair of new AI Workbench notebooks you can use to predict and analyze customer churn rates. By adjusting the input in the Parameters tab, you can customize and apply these machine learning models to your BlueConic data without writing any code, to examine customer churn rates.
New Predict Propensity to Churn AI Notebook
Marketing teams can use the Predict Propensity to Churn notebook in AI Workbench to predict the probability that customers in a certain customer segment will churn.
You can also use this AI model to predict the customer attrition for other profiles in a segment based on a particular profile property. For example, if you select 'gender' as a 'categorical profile property,' the notebook can create separate models for men and women.
Start by selecting a specific segment of customers in the parameter tab. Then choose a specific profile property which will be used to make propensity to churn models for the different categories of the profile property.
When you run this notebook in AI Workbench, the model saves the churn prediction to a profile property you select in the AI Workbench Parameters tab. In a few minutes, the results will be visible in your BlueConic profiles.
New Analyze Propensity to Churn AI Notebook
A companion notebook enables you to analyze and compare customer attrition or churn rates for different segments of customers. Using contract or subscription data, the model calculates subscription status and how long customers have subscribed or held a contract. For a given segment of customers, the model calculates churn risk per unit of time, and displays churn risk as a function of time.
Using the Parameters tab in AI Workbench, you can select a specific propensity to churn model and also customize colors used in your insight.
How do I get started?
Start by clicking the Add notebook button in AI Workbench and choosing one of the churn prediction notebooks.
Learn more about running AI models against BlueConic profile data with AI Workbench notebooks.
Importing transactions and events via the S3 Connection
We've added new features to the Amazon Web Services S3 Connection to import Timeline events to individual customer profiles. Introduced last spring, the BlueConic Timeline stores events to capture information about the timing and sequence of events for an individual BlueConic profile. A Timeline belongs to an individual profile and includes the set of all events for that profile, such as product orders, page views, calls, store visits, subscriptions, etc.
In the S3 connection, you can import files using the enhanced file selection tool to add order data from multiple CSV files relating to customer orders.
When you import data from several nested CSV files, a lightbox preview shows the file contents and columns.
Learn more about using the Amazon Web Services S3 Connection in BlueConic to import transactional data and timeline events.
We have plenty of new connections and enhancements in the works.
- Coming soon are new connections for exchanging profile data with Microsoft Power BI and Bluecore.
- Enhancements and updates to the existing Salesforce connection.