Business Agnostic Consultation Center Estimated Wait Times Prediction Using Deep Neural Networks

摘要

A method 800 for estimating an estimated waiting time 130 includes receiving a pending support request 120 from a user 10 . The pending support request is associated with a plurality of high-level features 202 including a number of active support agents 202a , a number of available support agents 202b , and a queue depth 202c . The method also includes predicting the estimated latency 130 for the user of the pending support request using the latency predictor model 270 configured to receive a plurality of high-level features as feature inputs. A latency predictor model is trained on a corpus of training assistance requests 120 H comprising a corresponding plurality of high-level features and a corresponding actual latency 202g. The method also includes providing the user with an estimated waiting time indicative of an estimated duration until a pending support request is answered.