Campaign Recommender models
The Campaign Recommender model is a ready-to-use data science model that identifies the most effective campaign to be sent for every customer based on past interactions.
The Campaign Recommender model explained
The ready-to-use Campaign recommender data science model ranks business-to-consumer (B2C) campaigns (recurring and one-time) for every customer in any instance based on the likelihood of conversions.
The model uses the following timeframes to assess data.
Campaign type | Timeframe of data |
---|---|
Weekly | Three months |
Monthly | One year |
Yearly | Three years |
One-time | One year |
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.
-
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 Channel Recommender model uses the following data.
For the model to successfully run:
-
Data needs to be ingested into all the input attributes below.
-
Make sure that the CustomerID attribute in the Event data object is populated.
-
Make sure that the CampaignID attribute in the Event data object is populated.
Data object | Attribute | Data type | Description |
---|---|---|---|
Customer and Campaign | SourceID | String |
The unique identifier for the source. |
Campaign | SourceID_Campaign | String | The unique identifier for the campaign that originates from the source. |
Event and Customer | SourceCustomerID | String | The unique identifier for the customer that originates from the source. |
Event and Customer | EventTS | Timestamp | The date and time when the event occurred. |
Event and Customer | Type | String | The type of event, such as View, Purchase, Buy, and Click. |
Event and Customer | Medium | String | The total number of purchase records for the customer. |
Event | ID | String | The unique identifier for the data object. |
Event and Customer | SourceCampaignID | String | The unique identifier for the campaign that originates from the source. |
Model outputs
You can review the ranked values generated for each campaign in the Campaign_Recommender data object. The following attributes will generate output values.
Attribute | Description |
---|---|
SourceCampaignRecommenderID | Concatenation of SourceMasterCustomerID and SourceCampaignID. |
SourceID_Campaign | The unique identifier for the campaign that originates from the source. |
SourceID | The unique identifier for the source. |
SourceCustomerID | The unique identifier for the customer that originates from the source. |
SourceCampaignID | The unique identifier for the campaign that originates from the source. |
Campaign_Rank | The rank of the campaign, based on the number of campaigns selected for the model. |
Create and use a Campaign recommender model
To create and use a Campaign Recommender model, you will need to do the following:
-
Follow the steps for Creating Campaign Recommender 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 Campaign Recommender 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.