Abstract: Disclosed are methods and systems for generating cure actions for improving a level of user engagement of a network. In some aspects, a method includes identifying network interaction relationships among a plurality of accounts of a computer network based on communication flows among the accounts, and tracking a level of engagement health of each of the accounts based on the interaction relationships over time. For each of the accounts, a determination is made as to whether the tracked level of engagement health meets a threshold requirement. For an account having a level of engagement health not meeting the threshold requirement, a cure action is selected based on one or more rules relating the tracked level of engagement health of the account to one or more predefined criteria. The cure action is then applied to the account.

Abstract: Disclosed in some examples are technical solutions to the existing technical problems in computer-implemented identification of anomalous events for distributed unstructured data existing in current supervised and unsupervised approaches. The anomaly detection system may use one or more unsupervised approaches that factor in small data sets using a volume-based time-invariant model. In some examples, in addition, a cross-category proportionality based model may also be utilized.

Abstract: Bugs/events that are reported by both users and the product are used to build an estimation model that relates the frequency/amount of received user bug reports to the number of products that are known to have the bug (as reported by the deployed products themselves.) This estimation model is then used to estimate the impact of bugs that are only discovered via user (i.e., free-form, unstructured) bug reports. In addition, the discovery of a bug via only user bug reports can be used to improve the data reported by the deployed products such that more information can be gathered about the nature and/or impact of the bug.