Abstract: This disclosure describes systems, devices, and techniques for managing resources in an enterprise network using lifecycle prediction. In an example method, a resource may be identified as operational within an enterprise network. An initial lifecycle of the resource may be estimated based at least partly on one or more characteristics of the resource. At least one trigger condition associated with the resource may be identified as having occurred. In response to identifying that the at least one trigger condition has occurred, an updated lifecycle of the resource may be estimated by applying at least one rule associated with the at least one trigger condition to the initial lifecycle. An expiration time of the resource may be determined based on the updated lifecycle. The resource may be replaced in advance of the expiration date of the resource.

Abstract: Historical information features that each comprise a supply chain performance indicator (such as a case fill rate performance indicator) for each of a plurality of different temporal windows are accessed and then at least some of the historical information features are weighted differently for at least some of the historical information features according to at least a first criterion to provide a training corpus. At least one machine learning model can then be trained using the training corpus to generate a machine learning model (or models) that are configured to predict supply chain performance.