Delivery Risk ML Model Details
When you click View details in the Delivery Risk tab, the following information is displayed for each ML model:
- Total no: The total number of user feedbacks received for the selected risk category such as Health and Safety risks or Litigation risks.
- Is a risk (Yes): Indicates if risks were identified as a percentage measure.
- Isn't a risk (No): Indicates if risks weren't identified as a percentage measure.
- <Model Name and version number> associated with the risk category displays
- Model status: The current status of the ML model. Displays as Enabled or
- Accuracy: The ratio of correct predictions to the total number of predictions.
- Precision: A measure of correctness on positive predictions, and a measure of how many are actually delayed out of all the activities that are predicted to be delayed.
- Recall: A measure of a model's ability to find all the positive results actually in the data. Of all the activities that are actually delayed, how many the model correctly identified.
- Last trained: The number of days since the model was last trained and the current status of the model as Yet to be trained, Require training, or up to date.
You can perform any of the following actions:
- Click Refresh data and retrain to retrain the ML model. This button is enabled if new data is available for the model.
- Click the Overflow Menu to:
Related Topics
Working With ML Workbench - New!
Last Published Thursday, December 7, 2023