Abstract: Systems, methods, and software for training a machine learning model. The system utilizes training data to train the machine learning model across multiple epochs. The system prepares additional training data by: selecting a set of samples that are unclassified, operating the machine learning model to predict labels that classify the samples, determining an uncertainty of the labels predicted by the machine learning model, calculating a ranking score for each of the samples in the set, selecting a subset of the samples that have more than a threshold ranking score, and submitting the subset to a client for replacement labels. The system receives the replacement labels from the client, and trains the machine learning model, using the subset of the samples as the training data. The labels predicted by the machine learning model for the subset are replaced with corresponding replacement labels from the client.

Abstract: Systems, methods, and software of processing a tabular dataset. In one embodiment, a system extracts raw association rules from the tabular dataset. Each of the raw association rules comprises a relationship between a set of antecedents and a single consequent, and corresponds to one or more transactions. The system determines potential rule merge groups of the raw association rules based on the antecedents, and determines one or more actual rule merge groups of the raw association rules in each potential rule merge group based on the transactions. The system combines the raw association rules in an actual rule merge group to generate a merged association rule. The system then generates a set of insights based on one or more merged association rules, and performs an operation based on the set of insights.

Abstract: Systems, methods, and software of processing a tabular dataset. In one embodiment, a system extracts raw association rules from the tabular dataset. Each of the raw association rules comprises a relationship between a set of antecedents and a single consequent, and corresponds to one or more transactions. The system determines potential rule merge groups of the raw association rules based on the antecedents, and determines one or more actual rule merge groups of the raw association rules in each potential rule merge group based on the transactions. The system combines the raw association rules in an actual rule merge group to generate a merged association rule. The system then generates a set of insights based on one or more merged association rules, and performs an operation based on the set of insights.

Abstract: The present disclosure describes systems and methods that provide a hybrid framework for augmenting statistical anomaly detection with contextual features, machine learning and human Subject Matter Expert (SME) input to learn significant characteristics of true anomalies for which alerts should be generated. The framework presented herein is domain agnostic and independent of the underlying statistical anomaly detection technique or the machine learning algorithm. The framework described herein is therefore applicable and adaptable to a number of real world service provider systems and applications, such as, for example, detecting network performance degradation in a service provider network or detecting anomalous conditions from data received from a sensor while filtering out false positives.

Abstract: A method, apparatus and system for improved community discovery that enables the accurate real-time determination of linkages between groups of individuals in a data-driven manner that is insensitive to noise and/or missing/dropped signals for automatically capturing the dynamic real-time interaction between individuals. No pre-defined parameters are necessary and the operations provide a fully data-driven solution that can be applied and adapted to diverse and highly dynamic environments in real-time in an automated fashion.

Abstract: The present disclosure describes systems and methods that provide a hybrid framework for augmenting statistical anomaly detection with contextual features, machine learning and human Subject Matter Expert (SME) input to learn significant characteristics of true anomalies for which alerts should be generated. The framework presented herein is domain agnostic and independent of the underlying statistical anomaly detection technique or the machine learning algorithm. The framework described herein is therefore applicable and adaptable to a number of real world service provider systems and applications, such as, for example, detecting network performance degradation in a service provider network or detecting anomalous conditions from data received from a sensor while filtering out false positives.

Abstract: A capability is provided for adaptive polling of a device based on a set of polling control regions configured to control polling of the device. The set of polling control regions is defined based on at least one of a set of control parameters and non-parametric control information. A transition within the set of polling control regions is determined based on a current polling control region and a target polling control region that is determined based on input information received while in the current polling control region. The input information may include at least one of values of one or more parameters in the set of parameters and non-parametric input information. The transition may include remaining in the current polling control region or transitioning to a new polling control region. The transition may be performed based on a rapid up controlled down (RUCD) transition scheme.

Abstract: A method, apparatus and system for improved community discovery that enables the accurate real-time determination of linkages between groups of individuals in a data-driven manner that is insensitive to noise and/or missing/dropped signals for automatically capturing the dynamic real-time interaction between individuals. No pre-defined parameters are necessary and the operations provide a fully data-driven solution that can be applied and adapted to diverse and highly dynamic environments in real-time in an automated fashion.

Abstract: The present disclosure generally discloses a problem event prediction capability. The problem event prediction capability may be configured to predict various types of problem events (e.g., customer problems, customer tickets, customer outages, network problems, network tickets, network outages, or the like, as well as various combinations thereof) based on various types of asynchronous machine data (e.g., alarms, alerts, triggers, machine logs, machine messages, diagnostic logs, diagnostic messages, or the like, as well as various combinations thereof). The problem event prediction capability may be configured to generate a set of problem prediction rules based on historical machine data and to apply the problem prediction rules to observed machine data in order to predict various types of problem events.

Abstract: Various exemplary embodiments relate to a method of determining the root cause of service degradation in a network, the method including determining a window of time; determining one or more abnormal Key Quality Indicators (KQIs) in the window; determining one or more abnormal Key Performance Indicators (KPIs) in the window; calculating a conditional probability that each of one or more KPIs is abnormal when a Key Quality Indicator (KQI) is normal; calculating a conditional probability that the each of one or more KPIs is abnormal when the KQI is abnormal; calculating a score for each KPI based upon a divergence of a Beta distribution for the conditional probability that each of one or more KPIs is abnormal when a KQI is normal and a Beta distribution for the conditional probability that the each of one or more KPIs is abnormal when the KQI is abnormal; and generating a representative root-cause list based upon the score for each KPI.

Abstract: Various exemplary embodiments relate to a method of determining the root cause of service degradation in a network, the method including determining a window of time; determining one or more abnormal Key Quality Indicators (KQIs) in the window; determining one or more abnormal Key Performance Indicators (KPIs) in the window; calculating a conditional probability that each of one or more KPIs is abnormal when a Key Quality Indicator (KQI) is normal; calculating a conditional probability that the each of one or more KPIs is abnormal when the KQI is abnormal; calculating a score for each KPI based upon a divergence of a Beta distribution for the conditional probability that each of one or more KPIs is abnormal when a KQI is normal and a Beta distribution for the conditional probability that the each of one or more KPIs is abnormal when the KQI is abnormal; and generating a representative root-cause list based upon the score for each KPI.

Abstract: An illustrative example computing system includes a parallel computing controller configured to communicate control information with a plurality of computing nodes over a virtual private network. A cloud computing controller is configured to receive a communication from the parallel computing controller. Based at least in part on the received communication, the cloud computing controller allocates cloud computing resources to facilitate data traffic communication involving at least one of the plurality of computing nodes.

Abstract: A method for deriving a composite tie metric for an edge between nodes of a telecommunication call graph includes receiving descriptive data with original values for descriptive attributes associated with a telecommunication call graph formed by edges between nodes. Each edge relates to two nodes. Each original value relates to an edge and a descriptive attribute forming an edge-attribute pair for the corresponding original value. The descriptive data is stored in a local storage device. Scaling factors for each descriptive attribute are determined taking into account a distribution of the original values for the corresponding descriptive attribute and a common base for the descriptive attributes. Weighting factors are determined for each descriptive attribute. The composite tie metric is computed for an edge based on the original value, scaling factor, and weighting factor for the descriptive attributes.

Abstract: A capability for classifying a device problem of a customer premises device of a customer is presented. The capability for classifying a device problem of a customer premises device of a customer may include receiving customer trouble ticket information of a trouble ticket associated with a customer, receiving customer device measurement information for a customer premises device of the customer, and classifying a device problem of the customer premises device based on text mining of the customer trouble ticket information and based on the customer device measurement information.

Abstract: A capability is provided for adaptive polling of a device based on a set of polling control regions configured to control polling of the device. The set of polling control regions is defined based on at least one of a set of control parameters and non-parametric control information. A transition within the set of polling control regions is determined based on a current polling control region and a target polling control region that is determined based on input information received while in the current polling control region. The input information may include at least one of values of one or more parameters in the set of parameters and non-parametric input information. The transition may include remaining in the current polling control region or transitioning to a new polling control region. The transition may be performed based on a rapid up controlled down (RUCD) transition scheme.

Abstract: An illustrative example computing system includes a parallel computing controller configured to communicate control information with a plurality of computing nodes over a virtual private network. A cloud computing controller is configured to receive a communication from the parallel computing controller. Based at least in part on the received communication, the cloud computing controller allocates cloud computing resources to facilitate data traffic communication involving at least one of the plurality of computing nodes.

Abstract: A capability is provided for adaptive polling of a device based on a set of polling control regions configured to control polling of the device. The set of polling control regions is defined based on at least one of a set of control parameters and non-parametric control information. A transition within the set of polling control regions is determined based on a current polling control region and a target polling control region that is determined based on input information received while in the current polling control region. The input information may include at least one of values of one or more parameters in the set of parameters and non-parametric input information. The transition may include remaining in the current polling control region or transitioning to a new polling control region. The transition may be performed based on a rapid up controlled down (RUCD) transition scheme.

Abstract: A capability is provided for adaptive polling of a device based on a set of polling control regions configured to control polling of the device. The set of polling control regions is defined based on at least one of a set of control parameters and non-parametric control information. A transition within the set of polling control regions is determined based on a current polling control region and a target polling control region that is determined based on input information received while in the current polling control region. The input information may include at least one of values of one or more parameters in the set of parameters and non-parametric input information. The transition may include remaining in the current polling control region or transitioning to a new polling control region. The transition may be performed based on a rapid up controlled down (RUCD) transition scheme.

Abstract: Various embodiments provide a method and apparatus of providing a non-overlapping ring-mesh network topology which reduces costs (e.g., the number of network links) while providing resiliency to failure and meeting QoS requirements (e.g., network delay attributed to traversing the network architecture). In particular, a set of target nodes belonging to a cluster are connected through N rings. Each node is member of all N rings and no link between nodes in a ring is duplicated in another ring.

Abstract: A system and method for generating a subscriber churn prediction includes receiving call detail records from a network operator detailing communication between subscribers of the network operator and determining tie-strengths between subscribers based on the call detail records. The system and method further includes generating a net churn influence accumulated at each subscriber from the tie-strengths by propagating churner influence between subscribers due to churn events.