Abstract: A computer product and methodology is contemplated for adaptively serving hold content during an automated communication session. This includes training a machine learning model with a set of training data that includes a feature of hold duration times during historical automated communication sessions. In response to encountering a computer transaction request during a new automated communication session, a hold time duration is predicted for executing the computer transaction request based on obtaining an inference from the machine learning model. Whether to serve hold content in response to the computer transaction request is determined, based on a comparison of the predicted hold time duration to a predetermined threshold time interval.

Abstract: A computer product and methodology is contemplated for adaptively serving hold content during an automated communication session. This includes training a machine learning model with a set of training data that includes a feature of hold duration times during historical automated communication sessions. In response to encountering a computer transaction request during a new automated communication session, a hold time duration is predicted for executing the computer transaction request based on obtaining an inference from the machine learning model. Whether to serve hold content in response to the computer transaction request is determined, based on a comparison of the predicted hold time duration to a predetermined threshold time interval.