Use this action to automatically predict or recommend a value based on historical data and determine confidence in the prediction using a Predictive Model.
Before configuring this action, first you need to create a predictive model based on a Data Table if you haven’t already.
After configuring a Predictive Model, you will receive an email when the training is completed. This usually requires 30-90 minutes. The email will include guidance on configuring the Field: Make a Prediction action for that specific model.
The alphanumeric ID of the Predictive Model. This will be included in the email that is sent to you after training a new Predictive Model. To locate it manually:
- When viewing the predictive model, copy the end of the URL from the browser address bar. For example, if the URL is: https://teamname.pushbot.com/build/ba7ed23a-f53b-4aa3-b9c9-01d4a54bbe03then the Predictive Model ID is: ba7ed23a-f53b-4aa3-b9c9-01d4a54bbe03
- To help keep output fields organized, choose an output field prefix to add to the beginning of each output field name as this action may output more than one field.
- The step’s name is used as the prefix by default.
This action will output a predicted value and a confidence rating of the prediction.
The confidence rating is a number from 0-100. Set up task conditions to assign a task to a person if the confidence rating is low, or skip that task and save some time if the confidence rating is high.
This action may generate multiple fields. To help keep output fields organized, the prefix above will be added to the beginning of each of the output field names, separated by two dashes. Each field will result as:
- The predicted value based on the input fields
- A 0-100 rating indicating the level of certainty of the accuracy of the prediction