Impact predictions based on incident-related data

A system for predicting impact on infrastructure elements based on incident ticket data, the system comprising:

• at least one processor;
• and
• at least one memory comprising computer program code, the at least one memory and the computer program code configured to cause the at least one processor to:
• receive an incident ticket, the incident ticket including data related to an incident occurred during an impact time period;
• perform natural language processing of the data included in the incident ticket to identify key fields;
• using the key fields, search metric data and event data associated with the incident ticket to identify anomalous events during an updated time period including the impact time period and additional time;
• generate predicted impact data for the updated time period based on the identified anomalous events, the predicted impact data identifying one or more infrastructure elements unidentified in the incident ticket;
• using the predicted impact data, generate one or more labeled incident tickets;
• using the one or more labeled incident tickets train an impact model;
• cause the trained impact model to predict a set of infrastructure elements likely to be impacted based on a newly received incident ticket;
• and
• update the newly received incident ticket with the predicted set of infrastructure elements.

One or more non-transitory computer storage media having computer-executable instructions embodied thereon, for predicting impact on infrastructure elements based on incident ticket data, wherein upon execution by at least one processor, the computer-executable instructions cause the processor to:

• receive an incident ticket, the incident ticket including data related to an incident occurred during an impact time period;
• perform natural language processing of the data included in the incident ticket to identify key fields;
• using the key fields, search metric data and event data associated with the incident ticket to identify anomalous events during an updated time period including the impact time period and additional time;
• generate predicted impact data for the updated time period based on the identified anomalous events, the predicted impact data identifying one or more infrastructure elements unidentified in the incident ticket;
• using the predicted impact data, generate one or more labeled incident tickets;
• using the one or more labeled incident tickets train an impact model;
• cause the trained impact model to predict a set of infrastructure elements likely to be impacted based on a newly received incident ticket;
• and
• update the newly received incident ticket with the predicted set of infrastructure elements.