Add predictors based on Interaction History
You can now define more accurate adaptive models, as they automatically use information from historical interactions to improve their predictive power. For example, an adaptive model for sales can automatically suggest a premium mobile plan for a customer who has recently enabled an additional service in their standard plan.
A list of predictors based in Interaction History summaries is enabled by default, without any additional setup, for all new adaptive models. The more channels are used for communicating with customers, the more predictors are automatically available in an adaptive model. To enhance the accuracy of predictions, two new predictors are added for every inbound communication via a channel, as demonstrated in the following example:
Enabling Interaction History predictors
By default, a new predictor is added for each unique combination of the Channel, Direction, and Outcome values in Interaction History.
For more information, see:
Published August 13, 2018 — Updated November 30, 2018