Abstract: Disclosed herein is a statistical approach, a win share approach, used to assign a win share value to content items. User interaction with content items is tracked, and a win share value is assigned to content items in response to a “winning” action performed by a user. Win shares associated with content items are used to identify content items that are to be presented, and can further be used to identify an optimal presentation, e.g., layout, presentation frequency, etc., of content items that is to be presented.

Abstract: In one embodiment, a network assurance service that monitors a network maps time series of values of key performance indicator (KPIs) measured from the network to lists of unique values from the time series. The service sets a target alarm rate for anomaly detection alarms raised by the network assurance service. The service uses an optimization function to identify a set of thresholds for the KPIs. The optimization function is based on: a comparison between the target alarm rate and a fraction of network issues flagged by the service as outliers, KPI thresholds selected based on the lists of unique values from the time series, and a number of thresholds that the KPIs must cross for the service to raise an alarm. The service raises an anomaly detection alarm for the monitored network based on the identified set of thresholds for the KPIs.

Abstract: Examples disclosed herein relate to systems and methods for deep learning enhanced garbage collection. Disclosed methods may include receiving, at a controller of an array, a time series dataset including a number of writes and a number of deletes; generating, by the controller, a tensor by encoding the time series data using a plurality of frequencies; determining a pattern in the time series data; generating a forecast of deletes based on the pattern; determining, based on the forecast, a number of cumulative deletes to the array at a predetermined time; at the predetermined time, comparing the forecasted number of cumulative deletes with a number of actual deletes to the array; and based on the comparison, scheduling a garbage collection (GC) algorithm to run on the array.

Abstract: In one embodiment, a network assurance service that monitors a network maps time series of values of key performance indicator (KPIs) measured from the network to lists of unique values from the time series. The service sets a target alarm rate for anomaly detection alarms raised by the network assurance service. The service uses an optimization function to identify a set of thresholds for the KPIs. The optimization function is based on: a comparison between the target alarm rate and a fraction of network issues flagged by the service as outliers, KPI thresholds selected based on the lists of unique values from the time series, and a number of thresholds that the KPIs must cross for the service to raise an alarm. The service raises an anomaly detection alarm for the monitored network based on the identified set of thresholds for the KPIs.

Abstract: Provided are systems and methods for a cloud security system that learns patterns of user behavior and uses the patterns to detect anomalous behavior in a network. Techniques discussed herein include obtaining activity data from a service provider system. The activity data describes actions performed during use of a cloud service over a period of time. A pattern corresponding to a series of actions performed over a subset of time can be identified. The pattern can be added a model associated with the cloud service. The model represents usage of the cloud service by the one or more users. Additional activity data can be obtained from the service provider system. Using the model, a set of actions can be identified in the additional activity data that do not correspond to the model. The set of actions and an indicator that identifies the set of actions as anomalous can be output.

Abstract: Techniques are provided for determining, by a coupon distributor, a value for a coupon of a product or service that will be provided by a coupon provider. The coupon provider provides, to the coupon distributor, one or both of a budget value that indicates an amount the coupon provider is willing to pay the coupon distributor for distributing the coupon, and a redemption rate that indicates one or more target redemption rates. The coupon provider uses a coupon value equation to calculate the coupon value based on a budget value and a redemption rate. The coupon provider might estimate that no coupon value will allow the coupon provider to stay within the budget and ensure that the actual redemption rate will be close to a particular redemption rate, which may or may not be specified by the coupon distributor.

Abstract: In one embodiment, a network assurance service that monitors a network maps time series of values of key performance indicator (KPIs) measured from the network to lists of unique values from the time series. The service sets a target alarm rate for anomaly detection alarms raised by the network assurance service. The service uses an optimization function to identify a set of thresholds for the KPIs. The optimization function is based on: a comparison between the target alarm rate and a fraction of network issues flagged by the service as outliers, KPI thresholds selected based on the lists of unique values from the time series, and a number of thresholds that the KPIs must cross for the service to raise an alarm. The service raises an anomaly detection alarm for the monitored network based on the identified set of thresholds for the KPIs.

Abstract: In one embodiment, a network assurance service that monitors a network receives a plurality of key performance indicators (KPIs) for a networking device in the network over time. The network assurance service represents relationship changes between the KPIs over time as a set of one or more KPI trajectories. The network assurance service uses a machine learning-based model to determine that a behavior of the networking device is anomalous, based on the one or more KPI trajectories. The network assurance service provides an indication of the anomalous behavior of the networking device to a user interface.

Abstract: Determining the importance of network devices based on a discovered topology, managed endpoints, and activity may be provided. First, topology data may be received corresponding to a network comprising a plurality of devices. Then, a topology matrix may be created representing the topology data. Next, a stationary matrix may be determined from the topology matrix. The stationary matrix may indicate a relative importance of each of the plurality of devices within the network. A health score may then be determined for at least one of the plurality of devices based on the relative importance of the at least one of the plurality of devices. The health score may be determined using the stationary matrix.

Abstract: In one embodiment, a network assurance service that monitors a network maps time series of values of key performance indicator (KPIs) measured from the network to lists of unique values from the time series. The service sets a target alarm rate for anomaly detection alarms raised by the network assurance service. The service uses an optimization function to identify a set of thresholds for the KPIs. The optimization function is based on: a comparison between the target alarm rate and a fraction of network issues flagged by the service as outliers, KPI thresholds selected based on the lists of unique values from the time series, and a number of thresholds that the KPIs must cross for the service to raise an alarm. The service raises an anomaly detection alarm for the monitored network based on the identified set of thresholds for the KPIs.

Abstract: Determining the importance of network devices based on a discovered topology, managed endpoints, and activity may be provided. First, topology data may be received corresponding to a network comprising a plurality of devices. Then, a topology matrix may be created representing the topology data. Next, a stationary matrix may be determined from the topology matrix. The stationary matrix may indicate a relative importance of each of the plurality of devices within the network. A health score may then be determined for at least one of the plurality of devices based on the relative importance of the at least one of the plurality of devices. The health score may be determined using the stationary matrix.

Abstract: In one embodiment, a network assurance service that monitors a network receives a plurality of key performance indicators (KPIs) for a networking device in the network over time. The network assurance service represents relationship changes between the KPIs over time as a set of one or more KPI trajectories. The network assurance service uses a machine learning-based model to determine that a behavior of the networking device is anomalous, based on the one or more KPI trajectories. The network assurance service provides an indication of the anomalous behavior of the networking device to a user interface.

Abstract: In one embodiment, a network assurance service that monitors a network maps time series of values of key performance indicator (KPIs) measured from the network to lists of unique values from the time series. The service sets a target alarm rate for anomaly detection alarms raised by the network assurance service. The service uses an optimization function to identify a set of thresholds for the KPIs. The optimization function is based on: a comparison between the target alarm rate and a fraction of network issues flagged by the service as outliers, KPI thresholds selected based on the lists of unique values from the time series, and a number of thresholds that the KPIs must cross for the service to raise an alarm. The service raises an anomaly detection alarm for the monitored network based on the identified set of thresholds for the KPIs.

Abstract: Techniques are provided for determining, by a coupon distributor, a value for a coupon of a product or service that will be provided by a coupon provider. The coupon provider provides, to the coupon distributor, one or both of a budget value that indicates an amount the coupon provider is willing to pay the coupon distributor for distributing the coupon, and a redemption rate that indicates one or more target redemption rates. The coupon provider uses a coupon value equation to calculate the coupon value based on a budget value and a redemption rate. The coupon provider might estimate that no coupon value will allow the coupon provider to stay within the budget and ensure that the actual redemption rate will be close to a particular redemption rate, which may or may not be specified by the coupon distributor.

Abstract: Techniques are provided for determining, by a coupon distributor, a value for a coupon of a product or service that will be provided by a coupon provider. The coupon provider provides, to the coupon distributor, one or both of a budget value that indicates an amount the coupon provider is willing to pay the coupon distributor for distributing the coupon, and a redemption rate that indicates one or more target redemption rates. The coupon provider uses a coupon value equation to calculate the coupon value based on a budget value and a redemption rate. The coupon provider might estimate that no coupon value will allow the coupon provider to stay within the budget and ensure that the actual redemption rate will be close to a particular redemption rate, which may or may not be specified by the coupon distributor.

Abstract: Provided are systems and methods for a cloud security system that learns patterns of user behavior and uses the patterns to detect anomalous behavior in a network. Techniques discussed herein include obtaining activity data from a service provider system. The activity data describes actions performed during use of a cloud service over a period of time. A pattern corresponding to a series of actions performed over a subset of time can be identified. The pattern can be added a model associated with the cloud service. The model represents usage of the cloud service by the one or more users. Additional activity data can be obtained from the service provider system. Using the model, a set of actions can be identified in the additional activity data that do not correspond to the model. The set of actions and an indicator that identifies the set of actions as anomalous can be output.

Abstract: Disclosed herein is a statistical approach, a win share approach, used to assign a win share value to content items. User interaction with content items is tracked, and a win share value is assigned to content items in response to a “winning” action performed by a user. Win shares associated with content items are used to identify content items that are to be presented, and can further be used to identify an optimal presentation, e.g., layout, presentation frequency, etc., of content items that is to be presented.

Abstract: Disclosed herein is a statistical approach, a win share approach, used to assign a win share value to content items. User interaction with content items is tracked, and a win share value is assigned to content items in response to a “winning” action performed by a user. Win shares associated with content items are used to identify content items that are to be presented, and can further be used to identify an optimal presentation, e.g., layout, presentation frequency, etc., of content items that is to be presented.

Abstract: Various embodiments describe systems and methods for optimizing the placement of digital offers on a digital medium.

Abstract: Techniques are provided for generating, by a coupon distributor, a score that represents a quality of a coupon campaign that a coupon provider offers to the coupon distributor. The score may be generated based on the brand of the product, the product category to which the product belongs, the coupon value, and the percentage discount reflected by the coupon. One or more of these factors may be based on historical data that indicates the success (or failure) of previous coupon campaigns (e.g., of the same product, brand, and/or product category, and/or similar coupon value). The coupon distributor uses the score to, e.g., determine whether to accept a proposed coupon campaign, project the number of prints/redemptions of the coupon campaign, determine how to present the coupon, determine an amount to charge for running the coupon campaign, and/or determine products or product categories of coupons to which the coupon distributor should seek.