DocumentationMix ModelerMix Modeler Guide

Models overview

Last update: Tue Feb 25 2025 00:00:00 GMT+0000 (Coordinated Universal Time)

CREATED FOR:

  • User
  • Admin

The model functionality in Mix Modeler allows you to configure, train, and score models specific to your business objectives. The training and scoring supports AI-driven transfer learning between multitouch attribution and marketing mix modeling.

The models are based on the harmonized data that you create as part of the Mix Modeler application workflow.

A model in Mix Modeler is a machine learning model employed to measure and predict a specified outcome based on a marketer’s investments. Marketing touchpoints and summary-level data can be used as an input. Mix Modeler allows you to create variants of models based on different sets of variables, dimensions, and outcomes, such as revenues, units sold, leads.

A model requires:

  • One conversion.
  • One or more marketing touchpoints (channels) comprised of summary-level data, marketing touchpoint data (event data) or both.
  • A configurable lookback window.
  • A configurable training window.

A model can optionally include:

  • External factors.
  • Internal factors.
  • Prior knowledge of marketing contributions from other sources such as past stakeholder experience, incrementally testing, other models.
  • Spend share, which uses relative spend share as a proxy when marketing data is sparse.

When a model is first created, the creation immediately kicks off the training and scoring process. After the completion of the initial training and scoring run, model insights will be available for review. A model may subsequently be re-trained. Also, data may be added to the model which requires you to re-score the model manually. Re-trainng and re-scoring are an iterative process as new findings and information emerge and adjustments are needed to obtain a model fit that is most appropriate for your business objectives.

Build models

To build a model, use the Mix Modeler step-by-step guided model configuration flow available when you select Open model canvas. See Build models for more details.

Manage models

To view a table of your current models, in the Mix Modeler interface:

  1. Select Models from the left rail.

  2. You see a table of the current models.

    The table columns specify details about the model.

    table 0-row-2 1-row-2 2-row-2 3-row-2 4-row-2 5-row-2 6-row-2 layout-auto
    Column name Details
    Name Name of the model
    Description Description of the model
    Conversion event The conversion you have selected for the model.
    Run frequency The running frequency of training the model.
    Last run The date and time of the last training of the model.
    Status The status of the model.

    The reported status of the model is dependent on where a model is within its lifecycle. For example, whether a model is created, (re-)trained successfully or not, or (re-)scored successfully or not.

    In the table below:

    • Checkmark - indicates a successful execution of a step in the model lifecycle.
    • Clock - indicates a current ongoing execution of a step in the model lifecycle.
    • Close - indicates a failed execution of a step in the model lifecycle.
    table 0-row-6 1-row-6 2-row-6 3-row-6 4-row-6 5-row-6 6-row-6 7-row-6 8-row-6 9-row-6 10-row-6 11-row-6 12-row-6 13-row-6 2-align-center 3-align-center 4-align-center 5-align-center 6-align-center 9-align-center 10-align-center 11-align-center 12-align-center 13-align-center 16-align-center 17-align-center 18-align-center 19-align-center 20-align-center 23-align-center 24-align-center 25-align-center 26-align-center 27-align-center 30-align-center 31-align-center 32-align-center 33-align-center 34-align-center 37-align-center 38-align-center 39-align-center 40-align-center 41-align-center 44-align-center 45-align-center 46-align-center 47-align-center 48-align-center 51-align-center 52-align-center 53-align-center 54-align-center 55-align-center 58-align-center 59-align-center 60-align-center 61-align-center 62-align-center 65-align-center 66-align-center 67-align-center 68-align-center 69-align-center 72-align-center 73-align-center 74-align-center 75-align-center 76-align-center 79-align-center 80-align-center 81-align-center 82-align-center 83-align-center 86-align-center 87-align-center 88-align-center 89-align-center 90-align-center 93-align-center 94-align-center 95-align-center 96-align-center 97-align-center
    Status Create Train Score Re-train Re-score
    In progress Checkmark
    In progress Checkmark Clock
    In progress Checkmark Checkmark Clock
    In progress Checkmark Checkmark Checkmark Clock
    In progress Checkmark Checkmark Checkmark Checkmark Clock
    Training failed Checkmark Close
    Training failed Checkmark Checkmark Checkmark Close
    Training successful Checkmark Checkmark
    Training successful Checkmark Checkmark Checkmark Checkmark
    Scoring failed Checkmark Checkmark Close
    Scoring failed Checkmark Checkmark Checkmark Checkmark Close
    Scoring successful Checkmark Checkmark Checkmark
    Scoring successful Checkmark Checkmark Checkmark Checkmark Checkmark

  3. To change the columns displayed for the list, select Column settings and toggle columns on Check or off.

You can take the following actions on a specific model.

Model insights

The model insights functionality is only available on successfully trained and scored models.

To view the insights of a model:

  1. Select Models from the left rail.

  2. Select the model name.

You are redirected to Model Insights.

View details

To view more details of a model:

  1. Select Models from the left rail.

  2. Select Info for a model to show a pop-up with details.

Duplicate

You can quickly duplicate a model.

  1. Select Models from the left rail.

  2. Select More for a model, and from the context menu select Duplicate.

You are redirected to the steps to create a new model, with a proposed name composed of the original model’s name appended with (Copy) (n).

Edit

You can edit the name, description and the scheduling of training and scoring of a model.

  1. Select Models from the left rail.

  2. Select More for a model, and from the context menu select Edit.

    In the Edit model dialog:

    • Enter a new Name and Description.

    • To enable scheduling, enable Status. You can only enable scheduling for models that are trained and scored.

      1. Select a Scoring frequency:

        • Daily: Enter a valid time (for example 05:22 pm) or use Clock .
        • Weekly: Select a day of the week and enter a valid time (for example 05:22 pm) or use Clock .
        • Monthly: Select a day of the month from the Run on every dropdown menu and enter a valid time (for example 05:22 pm) or use Clock .

      2. Select a Training frequency from the dropdown menu: Monthly, Quarterly, Yearly, or None.

      Edit a model

  3. Select Save.

Re-train

Re-train a model is only available on successfully trained models.

Consider to re-train a model when you want to:

  • Include new incremental marketing and factor data. For example, over the last quarter, market dynamics have changed or your marketing data distribution has changed significantly.

To re-train a model:

  1. Select Models from the left rail.

  2. Select More for a model, and from the context menu select Train. Alternatively, select DataRefresh Train from the blue action bar.

    In the Train model dialog, select the option to:

    • Train model with last 2 years of marketing data, or
    • Train model using specific date range of data.
      Specify the date range. You can use the Calendar to select a date range. You have to select a data range with a minimum of one year.

    Re-train a model

  3. Select Train to re-train the model.

Score or re-score

You can incrementally score a model based on new marketing data or re-score a model for a specific date range.

Consider to re-score a model when you want to:

  • Correct incorrect marketing data. For example, the recent paid search data you included in the training and scoring of the model missed a week of data.
  • Use new incremental marketing data that has become available through updates in the datasets you have configured as part of your harmonized data.

To score or re-score a model:

  1. Select Models from the left rail.

  2. Select More for a model, and from the context menu select Score. Alternatively, select DataRefresh Score from the blue action bar.

    In the Score marketing data dialog, select the option to:

    • Score new marketing data from mm/dd/yyyy, to score your model incrementally using new marketing data, or
    • Score specific date range of marketing data to re-score for a specific date range.
      Specify the date range. You can use the Calendar to select a date range.

    Re-train a model

  3. Select Score. When re-scoring a model using a specific data range, you see an Existing model is replaced dialog, prompting you to confirm to replace the model with new scores for the selected date range. Select Replace model to confirm.

Delete models

To delete a model:

  1. Select Models from the left rail.
  2. Select More for a model, and from the context menu select Delete. Alternatively, select Delete Delete from the blue action bar.
  3. Select Delete in the Delete model confirmation dialog to delete the model. Select Cancel to cancel.

To delete multiple models:

  1. Select multiple models.
  2. From the blue action bar, select Delete Delete to delete the models.
  3. Select Delete in the Delete x models confirmation dialog to delete the models. Select Cancel to cancel.
recommendation-more-help
d5f9b631-c793-4214-8dc7-f78d1750e4f4