Abstract: Methods, apparatus, and processor-readable storage media for identifying and remediating anomalies through cognitively assorted machine learning algorithms are provided herein. A computer-implemented method includes: identifying, using system log data, a target variable based at least in part on correlations between a set of performance indicators of a system and the target variable, and threshold values for the performance indicators relative to the target variable; generating an inference model to predict when the system will enter an adverse state and identify one or more root causes of the system entering the adverse state; using machine reinforcement learning to determine an action policy including actions that remediate the adverse state; predicting that the system will enter the adverse state by applying the inference model to further system log data; and automatically executing one or more actions of the action policy in response to the prediction.

Abstract: Methods, apparatus, and processor-readable storage media for identifying and remediating anomalies through cognitively assorted machine learning algorithms are provided herein. A computer-implemented method includes: identifying, using system log data, a target variable based at least in part on correlations between a set of performance indicators of a system and the target variable, and threshold values for the performance indicators relative to the target variable; generating an inference model to predict when the system will enter an adverse state and identify one or more root causes of the system entering the adverse state; using machine reinforcement learning to determine an action policy including actions that remediate the adverse state; predicting that the system will enter the adverse state by applying the inference model to further system log data; and automatically executing one or more actions of the action policy in response to the prediction.

Abstract: In an embodiment, a method includes identifying a particular service of a service-oriented architecture. The method also includes querying a data store for callers of the particular service, where the querying yields load-balancing internet protocol (IP) addresses of the callers in relation to proportional numbers of calls to the particular service. The method also includes resolving the load-balancing IP addresses to host IP addresses of the callers of the particular service. The method also includes resolving the host IP addresses to host names of particular hosts. The method also includes identifying applications of the particular hosts via the host names. The method also includes generating a data object including the host names, identifiers of the applications, and information related to the proportional numbers of calls to the particular service.

Abstract: In an embodiment, a method includes identifying a particular service of a service-oriented architecture. The method also includes querying a data store for callers of the particular service, where the querying yields load-balancing internet protocol (IP) addresses of the callers in relation to proportional numbers of calls to the particular service. The method also includes resolving the load-balancing IP addresses to host IP addresses of the callers of the particular service. The method also includes resolving the host IP addresses to host names of particular hosts. The method also includes identifying applications of the particular hosts via the host names. The method also includes generating a data object including the host names, identifiers of the applications, and information related to the proportional numbers of calls to the particular service.