System recommendations based on incident analysis

摘要

In one embodiment, a computer-implemented method includes obtaining incident data related to a plurality of servers, including a first server. Configuration data is obtained for each of the plurality of servers. The configuration data includes information about a set of one or more configuration items of the first server. A predictive modeler is trained to predict incident characteristics, based at least in part on the incident data and the configuration data. A modification is selected to the set of configuration items of the first server. Predicted incident characteristics of the first server are simulated, by a computer processor, based on the selected modifications. It is recommended that the selected modifications be made to the first server if predetermined criteria are met by the simulation.

主权项

1. A computer-implemented method, comprising:
obtaining incident data for a server; obtaining configuration data for the server, wherein the configuration data includes information about data associated with a set of one or more configuration items of the first-server; training a predictive modeler, based at least in part on the incident data and the configuration data, to predict incident characteristics of the server; selecting a modification to at least one configuration item in the set of configuration items; generating by a computer processor and using the trained predictive modeler, simulation data indicating one or more predicted incident characteristics of the server that are associated with the modification to the at least one configuration item; determining, based at least in part on the simulation data, a probability that the modification to the at least one configuration item results in a change in a categorization of the server from a problematic categorization to a non-problematic categorization, wherein the categorization of the server is based at least in part on at least one of a quantity or a severity of incidents associated with the server; determining that the probability meets or exceeds a predetermined probability; and outputting recommendation data indicating that the modification to the at least one configuration item is to be made to the server.