Train and score models
After you have built a model, the model is automatically trained and scored. You can manually retrain or rescore a model.
Train
Consider to retrain 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 retrain a model:
-
Select
-
Select
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
-
Select Train to retrain the model.
You can only retrain a model when the model is successfully trained.
Score
You can incrementally score a model based on new marketing data or rescore a model for a specific date range.
Consider to rescore 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 rescore a model:
-
Select
-
Select
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 rescore for a specific date range.
Specify the date range. You can use the
-
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.