Campaign Attribution models
The Campaign Revenue Attribution (Revenue and Non-Revenue) model is a ready-to-use data science model that measures the effectiveness of campaigns by analyzing touch points that drive revenues and conversions.
The Campaign Attribution model explained
There are two types of Campaign Attribution models. The Revenue Campaign Attribution model measures the effectiveness of campaigns by assigning a monetary value to each campaign. The Non-Revenue Campaign Attribution model measures the effectiveness of campaigns by assigning a percentage attribution value to each campaign. The model calculates the 'Attribution Percentage' as a percentage value of campaigns converted to total conversions for each individual campaign.
Each model considers all the touch points that contributed to the conversion of the campaign.
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 Campaign Attribution algorithm, you will need to define the following additional parameters.
-
Type: Select if the type of attribution, Revenue or Non-Revenue.
-
Lookback window: Select the number of days as a lookback window (7, 14, 30, 45, 60, 90, or 180 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 Campaign Attribution model uses the following data.
For the model to successfully run:
- Data needs to be ingested into all the input attributes below.
- Revenue needs to be for a single currency type.
- Only one product can be considered.
- The CustomerID attribute in the Event data object needs to be populated.
- The CampaignID attribute in the Event data object needs to be populated.
Data object | Attribute | Data type | Description |
---|---|---|---|
Event | EventTS | Timestamp | The date and time when the activity occurred. |
Event | Quantity | Integer |
The quantity ordered (only for revenue attribution) |
Event | ProductID | String | The unique identifier for the product. |
Event | CampaignID | String | The unique identifier for the campaign. |
Event | ID | String | The unique identifier for the data object. |
Event | OrderTotal | Float | The total order amount. |
Order | OrderEntryTS | Timestamp | The date and time when the order/sale happened. |
Account or Customer | Account_ID | String | The unique identifier for the B2B account. |
Model outputs
You can review values generated as monetary values for each campaign and product in the CampaignAttribution data object. The following attributes will generate output values.
Revenue attribution models generate output values in the AttributionValue attribute. Non-Revenue attribution models generate output values in the AttributionConversion and AttributionPercentage attributes.
Attribute | Description | Data type | Is Key attribute? |
---|---|---|---|
SourceCampaignID | The unique ID for the campaign. | String | Yes |
SourceProductID | The unique ID for the product. | String | Yes |
SourceCampaignAttributionID | The unique ID for the data object. | String | Yes |
AttributionValue | The attribution value represented in currency for revenue attribution models | Float | No |
AttributionConversion | The campaign conversion value for non-revenue attribution models | Float | No |
AttributionPercentage | The attribution value represented as a percentage for non-revenue attribution models | Float | No |
Quarter | The financial quarter for which revenue is aggregated | String | No |
Type | The type of attribution: Revenue or Non-Revenue. | String | No |
Create and use an Attribution model
To create and use an Attribution model, you will need to do the following:
-
Follow the steps for Creating Campaign Attribution models.
-
After creating the model, Run the training job for the model.
After the model runs and creates output values, you can do the following:
-
Access Campaign Attribution 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.