Abstract: Assigning support tickets to support agents is described. A system receives support tickets and trains a machine-learning model to identify support agents who had experiences resolving support tickets of multiple complexities. The system receives a support ticket, identifies a topic of the support ticket, and estimates a complexity of the support ticket. The system identifies support agents who have skills handling the topic of the support ticket. The machine-learning model identifies support agents who have experiences resolving support tickets of the estimated complexity. The system projects workload availabilities, of identified support agents, for the support ticket. The system generates support agent scores based on the skills handling the topic, the experiences resolving support tickets of the estimated complexity, and the projected workload availabilities for the support ticket. The system assigns, based on the support agent scores, the support ticket to an identified support agent.

Abstract: System derives training change factors for services provided for training product user, priority assigned to training service ticket initiated by training product user, times of service ticket interactions associated with training service ticket, and/or age of training service ticket, and also for times of states of training service ticket. System uses training service ticket and training change factors to train change-based machine-learning model to predict change-based training probability that training product user escalated service for training service ticket. System derives change factors for services provided for product user, priority assigned to service ticket initiated by product user, times of service ticket interactions associated with service ticket, and/or age of service ticket, and also for times of states of training service ticket.

Abstract: System derives training change factors for services provided for training product user, priority assigned to training service ticket initiated by training product user, times of service ticket interactions associated with training service ticket, and/or age of training service ticket, and also for times of states of training service ticket. System uses training service ticket and training change factors to train change-based machine-learning model to predict change-based training probability that training product user escalated service for training service ticket. System derives change factors for services provided for product user, priority assigned to service ticket initiated by product user, times of service ticket interactions associated with service ticket, and/or age of service ticket, and also for times of states of training service ticket.

Abstract: Predicting end-of-life support deprecation is described. A system receives an identification of a product, and then identifies support request records associated with the product. The system identifies support information associated with the support request records. A predictive model uses the support information to predict a deprecation for the product. The system outputs the prediction of the deprecation for the product.

Abstract: System receives historical text block, creates historical features for historical text block's historical text lines. System trains machine-learning model to cluster historical features into historical features clusters based on their similarities. System identifies historical features cluster as historical human text cluster. System classifies each historical text line for historical human text cluster as human text, and each historical text line for other historical features clusters as machine text. System receives text block, creates features for text block's text lines. System applies trained machine-learning model to cluster features into features clusters based on their similarities. System identifies features cluster as human text cluster. System classifies each text line for human text cluster as human text, and each text line for other features clusters as machine text.

Abstract: A support ticket summarizer, similarity classifier, and resolution forecaster are described. A system trains a machine learning model to identify topic sequences for support ticket communications, identify topic sequences that are classified as similar, and predict subsequent topics for multiple support ticket communications, in response to receiving the support ticket communications. The machine learning model receives a communication for a support ticket, and then identifies a sequence of topics for the communication for the support ticket. The machine-learning model identifies historical sequences of topics, for historical support tickets, which are classified as similar to the sequence of topics. The machine-learning model uses the historical sequences of topics to predict at least one subsequent topic for the sequence of topics. The system outputs the at least one subsequent topic.

Abstract: A support ticket summarizer, similarity classifier, and resolution forecaster are described. A system trains a machine learning model to identify topic sequences for support ticket communications, identify topic sequences that are classified as similar, and predict subsequent topics for multiple support ticket communications, in response to receiving the support ticket communications. The machine learning model receives a communication for a support ticket, and then identifies a sequence of topics for the communication for the support ticket. The machine-learning model identifies historical sequences of topics, for historical support tickets, which are classified as similar to the sequence of topics. The machine-learning model uses the historical sequences of topics to predict at least one subsequent topic for the sequence of topics. The system outputs the at least one subsequent topic.

Abstract: Assigning support tickets to support agents is described. A system receives support tickets and trains a machine-learning model to identify support agents who had experiences resolving support tickets of multiple complexities. The system receives a support ticket, identifies a topic of the support ticket, and estimates a complexity of the support ticket. The system identifies support agents who have skills handling the topic of the support ticket. The machine-learning model identifies support agents who have experiences resolving support tickets of the estimated complexity. The system projects workload availabilities, of identified support agents, for the support ticket. The system generates support agent scores based on the skills handling the topic, the experiences resolving support tickets of the estimated complexity, and the projected workload availabilities for the support ticket. The system assigns, based on the support agent scores, the support ticket to an identified support agent.

Abstract: System derives training change factors for services provided for training product user, priority assigned to training service ticket initiated by training product user, times of service ticket interactions associated with training service ticket, and/or age of training service ticket, and also for times of states of training service ticket. System uses training service ticket and training change factors to train change-based machine-learning model to predict change-based training probability that training product user escalated service for training service ticket. System derives change factors for services provided for product user, priority assigned to service ticket initiated by product user, times of service ticket interactions associated with service ticket, and/or age of service ticket, and also for times of states of training service ticket.