Abstract: A computer-implemented method assesses an impact of a change management strategy implementation. A first change management index score is identified. A graph theory is used to compute a degree centrality and a betweenness centrality of nodes, based on an adjacency matrix. A change management strategy framework is deployed based on the degree centrality, the betweenness centrality, and a closeness in a social media chain, to transition to one of the nodes having a probability above a predetermined probability threshold of influencing a change from one state to another. Personas are created that are associated with a particular technology, the identified first change management index score, the degree centrality, and the betweenness centrality of the nodes. A Markov chain model transition matrix measures a second change management index score after a time t is measured. A change management strategy framework is altered based on a parametric regression or a polynomial regression.

Abstract: A method includes using, by one or more processors of a computer system, a cognitive model to estimate software development parameters for a software development project based on one or more similar past projects, and automatically assigning, by the one or more processors of the computer system, story points to sprints of the software development project based on the estimated software development parameters.

Abstract: Computer implemented methods, systems, and computer program products include program code executing on a processor(s) that ingests data from one or more computing environments, where the data is related to applications. The processor(s) identifies, based on utilizing topic modeling and latent semantic analysis of the data, homogenous applications among the applications, which include analyzing subdata handled by each application and functionalities of each application; the homogenous applications comprise similarities in the data and in the functionalities. The processor(s) determines overlapping data among the homogenous applications based on the topic modeling, the latent semantic analysis, and term frequency-inverse document frequency of terms in the overlapping data. The processor(s) selects, from the overlapping data, training data. The processor(s) utilizes the training data to calculate weights for disposition metrics and the metrics to predict the resource dispositions for the applications.

Abstract: In various examples, a computer-implemented method includes: ingesting, by one or more computing devices, application deployment data for an application; generating, by the one or more computing devices, a cloud application deployment predictor data structure for the application; generating, by the one or more computing devices, objective functions for the cloud application deployment predictor data structure for the application; optimizing, by the one or more computing devices, between the objective functions for the application; and generating, by the one or more computing devices, based on the optimizing between the objective functions, a multi-cloud deployment map for the application.

Abstract: An end-to-end framework that provides for pair programming can determine a project intent. Programming requirements needed to fulfill the project intent can be identified. The programming requirements can be reduced into lower dimensions. The reduced programming requirements can be clustered into clusters. A common theme can be identified in each of the clusters. From at least one of the clusters having a common theme corresponding to the programming requirements, feasible pairs of developers can be selected. At least one optimal pair of developers can be determined among the feasible pairs using an optimization algorithm that optimizes the project intent.

Abstract: A method for a predictive insulation condition-based recommendation policy includes determining a present insulation level for an insulation layer on a cable providing power to an electronic device based on a current leakage test. The method also includes determining a current leakage and a confidence score for the insulation layer on the cable providing power to the electronic device utilizing a supervised machine learning model. The method also includes generating a decision framework for the electronic device based on the current leakage and the confidence score in response to determining to perform an action based on the decision framework for the electronic device, the method also includes performing the action based on the decision framework to address the current leakage for the insulation layer on the cable providing power to an electronic device.

Abstract: A method, a computer system, and a computer program product for restoration time predictions and optimized recovery solutions is provided. Embodiments of the present invention may include selecting a dataset based on time series data. Embodiments of the present invention may include building one or more models, wherein the one or more models include a classification and regression tree model, a cross validated decision tree model or a bootstrap aggregating model. Embodiments of the present invention may include selecting a model for predictions using decision trees to reduce a variance of the model. Embodiments of the present invention may include rebuilding the model based on additional data attributes. Embodiments of the present invention may include determining an outage prioritization for each outage node. Embodiments of the present invention may include transmitting results of the outage prioritization.

Abstract: Disclosed are techniques for training and utilizing a machine learning model for automatically accelerating technical incident triage. A historical dataset is combined from a plurality of sources corresponding to historical technical incidences and how they were resolved, including what persons or responders were involved in responding to the incident. This historical dataset is processed for input into a machine learning model which is trained to output a ranking of historical incidences based on similarity to an input incident. Machine logic then automatically selects a responder for the incident based on which available responders previously resolved the ranked historical incidences, selecting responders from the most similar historical incidences if they are available, and communicating information from the ranked historical incidences to assist in diagnosing and resolving the input incident.

Abstract: A method, system, and computer program product for implementing automated software application generation is provided. The method includes scanning source code for identifying missing elements of hardware and software parameters associated with functional operation of software for development. The hardware and software parameters are analyzed and converted into configurable digital bins. An automation parameter is generated. The automation parameter is associated with portions of the software configured for automatic development and generation. Corrective actions associated with automating development of the software are generated based on the automation parameter and it is determined that the automation parameter is within a specified range of the portions. The corrective actions are executed with respect to development of the software and the software is generated.

Abstract: A method includes receiving, by one or more processors of a computer system, historical data related to deployment characteristics and an architecture for past incidents occurring in a data warehouse, predicting, by the one or more processors of the computer system using neural network modeling, tickets related to a response to at least one incident occurring in the data warehouse, wherein the predicting is based on the deployment characteristics and the architecture of the data warehouse, considering, by the one or more processors of a computer system, a plurality of parameters to ascertain the predicted tickets, and providing, by the one or more processors of the computer system, incident ticket volume prediction including the predicted tickets to an incident management system interface reviewable by a user.

Abstract: A method includes using, by one or more processors of a computer system, a cognitive model to estimate software development parameters for a software development project based on one or more similar past projects, and automatically assigning, by the one or more processors of the computer system, story points to sprints of the software development project based on the estimated software development parameters.

Abstract: A method, system, and computer program product for predicting optimal service characteristics to execute predicted IT tickets. The method may include identifying deployment characteristics for an operational system based on an architecture of the operational system. The method may also include receiving implementation data in response to past incident tickets based on the deployment characteristics. The method may also include identifying relationships within the implementation data. The method may also include predicting a volume of new tickets based on the implementation data and the relationships between the implementation data. The method may also include predicting a resolution time for high severity tickets in the volume of new tickets. The method may also include determining preferred service characteristics based on the volume of the new tickets and the resolution time for the high severity tickets.

Abstract: A method, system, and computer program product for implementing automated software application generation is provided. The method includes scanning source code for identifying missing elements of hardware and software parameters associated with functional operation of software for development. The hardware and software parameters are analyzed and converted into configurable digital bins. An automation parameter is generated. The automation parameter is associated with portions of the software configured for automatic development and generation. Corrective actions associated with automating development of the software are generated based on the automation parameter and it is determined that the automation parameter is within a specified range of the portions. The corrective actions are executed with respect to development of the software and the software is generated.

Abstract: A method, a computer system, and a computer program product for restoration time predictions and optimized recovery solutions is provided. Embodiments of the present invention may include selecting a dataset based on time series data. Embodiments of the present invention may include building one or more models, wherein the one or more models include a classification and regression tree model, a cross validated decision tree model or a bootstrap aggregating model. Embodiments of the present invention may include selecting a model for predictions using decision trees to reduce a variance of the model. Embodiments of the present invention may include rebuilding the model based on additional data attributes. Embodiments of the present invention may include determining an outage prioritization for each outage node. Embodiments of the present invention may include transmitting results of the outage prioritization.

Abstract: A method, system, and computer program product for predicting optimal service characteristics to execute predicted IT tickets. The method may include identifying deployment characteristics for an operational system based on an architecture of the operational system. The method may also include receiving implementation data in response to past incident tickets based on the deployment characteristics. The method may also include identifying relationships within the implementation data. The method may also include predicting a volume of new tickets based on the implementation data and the relationships between the implementation data. The method may also include predicting a resolution time for high severity tickets in the volume of new tickets. The method may also include determining preferred service characteristics based on the volume of the new tickets and the resolution time for the high severity tickets.

Abstract: A failure rate model modeling a failure rate of a training functionality deployment in a training set of functionality deployments is constructed. The failure rate model is configured to receive functionality deployment data and output a corresponding failure rate prediction. Using the failure rate model, a set of functionality deployment failure rates is predicted, a functionality deployment failure rate in the set of functionality deployment failure rates corresponding to an upcoming functionality deployment. Using the set of functionality deployment failure rates, a deployment sequence of the set of upcoming functionality deployments is constructed to minimize a predicted overall failure rate of the set of upcoming functionality deployments. The deployment of each functionality deployment in the set of upcoming functionality deployments is caused, the deployment comprising activating the upcoming functionality program code according to the deployment sequence.

Abstract: Methods and systems for metrics for energy saving and response behavior are disclosed. A method includes: receiving, by a computing device, for each of a plurality of energy users, consumption time series data from a smart meter of the energy user; determining, by the computing device, for each of the plurality of energy users, demographic data of the energy user; clustering, by the computing device, the energy users based on the consumption time series data and the demographic data; identifying, by the computing device, a plurality of groups of energy users based upon the clustering; and determining, by the computing device, an energy saving program to associate with each of the plurality of groups.

Abstract: A failure rate model modeling a failure rate of a training functionality deployment in a training set of functionality deployments is constructed. The failure rate model is configured to receive functionality deployment data and output a corresponding failure rate prediction. Using the failure rate model, a set of functionality deployment failure rates is predicted, a functionality deployment failure rate in the set of functionality deployment failure rates corresponding to an upcoming functionality deployment. Using the set of functionality deployment failure rates, a deployment sequence of the set of upcoming functionality deployments is constructed to minimize a predicted overall failure rate of the set of upcoming functionality deployments. The deployment of each functionality deployment in the set of upcoming functionality deployments is caused, the deployment comprising activating the upcoming functionality program code according to the deployment sequence.

Abstract: A method collects from at least one power measuring device of an environment power consumption data indicating active power consumption during a timeframe by an electrical device in the environment. The method also collects operating parameter data indicating at least one operating parameter under which the electrical device operates during at least a portion of the timeframe. The method performs, based on observing an increase in power consumption of the electrical device during the timeframe, assessing extents of contribution by potential contributing factors to the increase in power consumption, the potential contributing factors including time-based degradation of the electrical device and the at least one operating parameter. The method outputs, based on the assessing, an indication of an extent of contribution of degradation of the electrical device to the increase in power consumption.

Abstract: A method collects from at least one power measuring device of an environment power consumption data indicating active power consumption during a timeframe by an electrical device in the environment. The method also collects operating parameter data indicating at least one operating parameter under which the electrical device operates during at least a portion of the timeframe. The method performs, based on observing an increase in power consumption of the electrical device during the timeframe, assessing extents of contribution by potential contributing factors to the increase in power consumption, the potential contributing factors including time-based degradation of the electrical device and the at least one operating parameter. The method outputs, based on the assessing, an indication of an extent of contribution of degradation of the electrical device to the increase in power consumption.