Create a model
To create a model, in the Models interface in Mix Modeler, select Open model canvas.
To build your custom AI-powered models, the interface provides a step-by-step guided model configuration flow.
-
In the Setup step:
-
Enter your model Name, for example
Demo model
. Enter a Description, for exampleDemo model to explore AI featues of Mix Modeler
. -
Select Next to continue to the next step. Select Cancel to cancel the model configuration.
-
-
In the Configure step:
-
In the Conversion goal section, within the container:
-
Enter a Conversion name for the conversion, for example
Conversion
-
Select a conversion from Select harmonized field, containing the available conversions you defined as part of Conversions in Harmonized datasets. For example, Online Conversion.
-
You can select Create new conversion to create a conversion directly from within the model configuration.
-
-
In the Marketing touchpoints section, you see a number of marketing touchpoint containers, corresponding to the marketing touchpoints you defined as part of Marketing touchpoints in Harmonized datasets.
-
For each container:
-
You can modify the Marketing touchpoint name.
-
Select a marketing touchpoint from Select marketing touchpoint.
-
You can select Create new marketing touchpoint to create a marketing touchpoint directly from within the model configuration.
-
-
To add a marketing touchpoint container, select Add marketing touchpoint.
-
To remove a marketing touchpoint container, within the container, select , and select Remove container from the context menu.
-
-
By default, a score is generated for all the data in your harmonized view. To only score a subset of the population, define one or more filters using containers in the Eligible data population section.
-
For each container, define one or more events.
-
For each event:
-
Select a metric or dimension from Select harmonized field.
-
Select the appropriate operator: equals, not equals, less than, greater than, starts with, doesn’t start with, ends with, doesn’t end with, contains, doesn’t contain, is in, or is not in.
-
Enter or select a value at Enter or select value.
-
-
To add an additional event in the container, select Add event.
-
To remove an event from the container, select .
-
To filter using all or any of multiple events defined in the container, select Any of or All of. The label correspondingly changes from Include … Or … to Include … And ….
-
-
To add an eligible data population container, select Add eligible population.
-
To remove an eligible data population container, within the container, select , and select Remove marketing touchpoint from the context menu.
-
-
To add datasets containing external factors to your model, use one or more containers in the External factors dataset section.
-
For each container:
-
Enter a Factor name at Enter factor.
-
Select a dataset from Select a dataset. You can select to manage datasets. See Datasets for more information.
-
-
To add an additional external factors dataset container, select Add external factor.
-
To remove an external factors dataset container, within the container, select , and select Remove external factor from the context menu.
-
-
To add datasets containing internal factors to your model, use one or more containers in the Internal factors dataset section.
-
For each container:
-
Enter a Factor name at Enter factor.
-
Select a dataset from Select a dataset. You can select to manage datasets. See Datasets for more information.
-
-
To add an additional internal factors dataset container, select Add internal factor.
-
To remove an additional internal factors dataset container, within the container, select , and Remove internal factor from the context menu.
-
-
To define the lookback window for the model, enter a value between
1
and52
in Give contribution credit to touchpoints occurring within … weeks prior to the conversion. -
Select Next to continue to the next step. If more configuration is needed, a red outline and text explains what additional configuration is required.
Select Back to go back to the previous step.
Select Cancel to cancel the model configuration.
-
-
In the Advanced step:
-
In the Define training window section, select between
-
Have Mix Modeler select a helpful training window and
-
Manually input a training window. When selected, define the number of years in Include events the following years prior to a conversion.
-
-
In the Spend share section:
- To use historical marketing investment ratios to inform the model when marketing data is sparse, activate Allow spend share.
-
In the Prior knowledge section:
-
Select the Rule type.
-
Specify contribution percentages for any of the channels listed under Name, using the Contribution proportion column.
-
Where appropriate, you can add for each channel a Level of confidence percentage.
-
When needed, use Clear all to clear all input values for the Contribution proportion and Level of confidence columns.
-
-
-
Select Finish to finish you model configuration.
-
In the Create instance? dialog, select Ok to trigger the first set of training and scoring runs immediately. Your model is listed with status ● Awaiting training.
Select Cancel to cancel.
-
If more configuration is needed, a red outline and text explains what additional configuration is required.
Select Back to go back to the previous step.
Select Cancel to cancel the model configuration.
-