ChannelMix | Predictive Modeling Optimization Dataset
The ChannelMix Predictive Modeling Optimization Dataset is used to power the Optimization section of the Pipeline with Predictive Modeling Dashboard. The dataset contains recommended spend per channel to optimize conversions for a given budget and date range. The recommendations are provided for multiple budgets and date ranges at once.
The dataset is refreshed at the same cadence as the Predictive Model is refreshed - monthly by default. Only the most recently produced results are displayed in the dashboard.
Field Name |
Field Type |
Description |
Conversions | DOUBLE PRECISION | Predicted number of conversions for optimized spend. |
Budget | DOUBLE PRECISION | The budget used for optimization. Base Budget * Budget Fraction. |
Optimization ID | TEXT | ID to uniquely identify a Model ID, Scenario Name, Budget Fraction grouping. |
Feature | TEXT | Name of the feature in the model. I.e. Paid Social, Display, etc. |
Spend | DOUBLE PRECISION | Recommended spend for this channel. |
Control | DOUBLE PRECISION | Value of control features for this recommendation. |
Model ID | TEXT | ID to identify the trained model used for optimization. |
Scenario Name | TEXT | The name for this date scenario e.g. Next Month, Next Nine Months, etc. |
Start Date | DATE | Starting date for optimization period. |
End Date | DATE | End date of optimization period. |
Target Variable Pretty | TEXT | A more descriptive name for the target variable to be displayed in the dashboard. |
Target Variable | TEXT | The name of the field the model is trained to predict. |
OneView Name | TEXT | The name of the OneView data is pulled from to model. |
Feature Type | TEXT | The name of the feature used to predict the target variable. |
Category | TEXT | Name of the category in the model. I.e. Client 1, Client 2, Line of Business 1, Line of Business 2, etc. |
Category Type | TEXT | The name of the category used to create a hierarchy |
Model Run Date | DATE | Date the model was trained. |
Cluster Number | INTEGER | The number of clusters the results are split into. |
Cluster ID | INTEGER | A unique ID given to all members of a cluster. |
Cluster Type | TEXT | Describes the way the cluster was defined. |
To Cache | TEXT | Is this one of the cached recommendations? If so, which one? |
Pacing ID | INTEGER | Unique ID for this recommendation (only cached recommendations) |
Most Recent Model | INTEGER | Is this record part of the output of the most recently ran model? |
Insert Date | TIMESTAMP | The date in which the record was loaded into the data warehouse |
ChannelMix Profile | TEXT | The ChannelMix Profile associated to the data |
Version 2022.4