High fidelity predictions of service ticket escalation

A computer-implemented method for high fidelity predictions of service ticket escalation, the computer-implemented method comprising:

• deriving training set change factor for a periodic observation that-service ticket interactions associated with the training set service ticket include a response to a request from the training set product user which natural language processing detects as a non-substantive response, such that the service ticket interactions continue to lack a substantive response to a request from the training set product user;
• training, using the training set service ticket, the training set change factor, and a change-based machine-learning model to predict a change-based training probability that the training set product user escalated service for the training set service ticket;
• deriving a change factor for a periodic observation that service ticket interactions associated with the service ticket includes a response to a request from the product user which natural language processing detects as a non-substantive response, such that the service ticket interactions continue to lack a substantive response to a request from the product user;
• predicting, by applying the change-based machine-learning model to the service ticket and the change factor, a change-based probability that the product user escalates service for the service ticket;
• outputting the change-based probability;
• and
• retraining, using data which includes the service ticket, the change factor, and the change-based probability, the change-based machine-learning model to predict a subsequent change-based training probability that a subsequent product user escalated service for a subsequent service ticket.

A computer program product, comprising a non-transitory computer-readable medium having a computer-readable program code embodied therein to be executed by one or more processors, the program code including instructions to:

• derive a training set change factor for a periodic observation that-service ticket interactions associated with the training set service ticket includes a response to a request from the training set product user which natural language processing detects as a non-substantive response, such that the service ticket interactions continue to lack a substantive response to a request from the training set product user;
• train, using the training set service ticket, the training set change factor, and a change-based machine-learning model to predict a change-based training probability that the training set product user escalated service for the training set service ticket;
• derive a change factor for a periodic observation that service ticket interactions associated with the service ticket includes a response to a request from the product user which natural language processing detects as a non-substantive response, such that the service ticket interactions continue to lack a substantive response to a request from the product user;
• predict, by applying the change-based machine-learning model to the service ticket and the change factor, a change-based probability that the product user escalates service for the service ticket;
• output the change-based probability;
• and
• retrain, using data which includes the service ticket, the change factor, and the change-based probability, the change-based machine-learning model to predict a subsequent change-based training probability that a subsequent product user escalated service for a subsequent service ticket.