Churn Propensity models
The Churn Propensity model is a ready-to-use data science model that scores measures a customer's likelihood to churn based on their transactional and behavioral patterns.
The Churn Propensity model explained
The Churn Propensity model helps marketers proactively identify potential churn in customers. Targeting these customers with relevant messaging and campaigns increases the ability to retain these customers.
Parameters of the model
When creating the model, you will need to define the following parameters for the model:
-
Algorithm: The algorithm is the piece of code that runs the model. When you select the Churn Propensity algorithm, you will need to define the following additional parameters.
-
Churn Criteria: Select the criteria the algorithm will use to run the model.
-
IsActive flag: The algorithm will determine if the IsActive attribute is True (customer isn't churned) or False (customer is churned). If selected, make sure the IsActive attribute is populated with data.
-
Custom - Zero orders: The algorithm will determine if customers are churned based on the Churn Window selection. For example, if you select a Churn Window of 30 days and a customer has no orders in the past 30 days, then the algorithm will tag the customer as churned.
-
-
Churn Window: Only applicable if you select Custom - Zero orders. Select the number of days for the churn window (30, 45, 60, or 90 days).
-
-
Queries: The queries selected for the model generate a dataset for model training and scoring.
-
Inputs: The inputs are query attributes from the Unity data model that are used for model training and scoring. You can't make changes to model inputs.
-
Outputs: The outputs are data objects and attributes from the Unity data model that are used to store the output values of the model. You can make updates to the default mapping of model outputs.
Model inputs
To generate values, the Churn Propensity model uses the following data.
Note: When you select Custom - Zero orders in the Churn criteria parameter, the algorithm auto-calculates the churn output values (ChurnScore and ChurnRisk).
For the model to successfully run:
- Data needs to be ingested into all the input attributes below.
-
Ensure the IsActive attribute is populated if you select IsActive flag in the Churn Criteria parameter.
Data object | Attribute | Data type | Description |
---|---|---|---|
Address | ZipCode | String | The zip code of the customer. |
Customer | SourceCustomerID | String | The unique identifier for the customer. |
Customer | SourceID | String | The source ID from the Customer data object. |
Customer | Age | Integer | The age of the customer. |
Customer | Gender | String | The gender of the customer. |
Customer | IsActive | Boolean | Indicates if an entity is active or inactive. |
Order | Status | String | The status of the order. |
Order | Total | String | The price of the product. |
Order Item | ProductID | String | The product ID from the Order Item data object. |
Order Item | OrderDate | Timestamp | The order date from the Order Item data object. |
Model outputs
Output values will be stored in the Customer_Churn data object. You can review the lead score values for each contact in the ChurnScore attribute. Each status from the ChurnRisk attribute (Very Low, Low, Medium, High, and Very High) is based on a lead score generated from 0 to 1. Review the specific values and assessments below.
The following attributes will generate output values.
Attribute | Description | Data Type | Is Key attribute? |
---|---|---|---|
SourceCustomer_churnID | The unique identifier for the data object. | String | Yes |
SourceID | The unique identifier for the source. | String | Yes |
SourceCustomerID | The unique identifier for the customer. | String | Yes |
ProductID | The unique identifier for the product. | String | No |
ChurnScore | The churn score generated for the customer. It is a numerical value from 0 to 1. | Float | No |
ChurnRisk | The status that assesses the risk of the customer churning. | String | No |
The ChurnRisk attribute will generate one of the following values based on the churn score.
Churn score | Churn risk |
---|---|
NA | Unknown |
0 - 0.2 | Very Low |
> 0.2 - 0.4 | Low |
> 0.4 - 0.6 | Medium |
> 0.6 - 0.8 | High |
> 0.8 - 1.0 | Very High |
Create and use a Churn Propensity model
To create and use a Churn Propensity model, you will need to do the following:
-
Follow the steps for Creating Churn Propensity models.
-
After creating the model, follow the steps for Running training and scoring jobs.
After the model runs and creates output values, you can do the following:
-
Access Churn Propensity data to review the values in the output attributes.
-
Learn more about Using data science data for the specific needs of your organization.
-
If needed, you can review the data science model details.