Jump to: navigation, search

Creating and Testing Predictors and Models

Predictors and models are key objects to create and optimize predictive routing.

  • Predictors enable you to analyze various factors that might affect a specific metric. For example, you might check how the matching between customer and agent languages, ages, genders, and locations affect the NPS score.
  • Models are built on a predictor and include the same target metric. Each model has a subset of the agent and customer features present in the dataset. The Feature Analysis report helps you to identify the features with the strongest impact on the target metric. You can create multiple models for the same predictor, each with a different set of features selected.

Before proceeding to create predictors, make sure you have created/uploaded the following data:

  • One or more Datasets
  • Agent Profile schema
  • Customer Profile schema

To start the process,

  1. Run the Feature Analysis report.
  2. Build a predictor focusing on the features that emerged as key in the Feature Analysis report.
  3. Create train, and test models based on the predictor.
This page was last edited on June 20, 2019, at 14:56.
Comments or questions about this documentation? Contact us for support!