Abstract: Methods and server systems for computing fraud risk scores for various merchants associated with an acquirer described herein. The method performed by a server system includes accessing merchant-related transaction data including merchant-related transaction indicators associated with a merchant from a transaction database. Method includes generating a merchant-related transaction features based on the merchant-related indicators. Method includes generating via risk prediction models, for a payment transaction with the merchant, merchant health and compliance risk scores, merchant terminal risk scores, merchant chargeback risk scores, and merchant activity risk scores based on the merchant-related transaction features. Method includes facilitating transmission of a notification message to an acquirer server associated with the merchant.

Abstract: An identification of a new primary snapshot created for a primary storage system is received. A change tracking time window that is at least a portion of a period between a first capture time associated with a previous primary snapshot and a second capture time associated with the new primary snapshot is determined. Entries of a storage log of the primary storage system occurring within the change tracking time window are analyzed to coalesce changes identified in the entries of the storage log occurring within the change tracking time window into a change tracking result set. The change tracking result set is used to identify at least a portion of data changes between the previous primary snapshot and the new primary snapshot to capture in a new backup snapshot stored at a secondary storage system.

Abstract: Embodiments include technologies to apply at least one machine learning model to features of a search query, features of a searcher user, features of a searchee content item, and features of a searchee user, produce a first outcome prediction that represents a probability of a first objective relating to engagement of the searcher user with a content item in an online system and a second outcome prediction that represents a probability of a second objective relating to engagement of the searchee user with the online system responsive to the engagement of the searcher user with the content item, apply a multi-objective optimization solver to the first objective, the second objective and an outcome prediction that is a combination of the first outcome prediction and the second outcome prediction, and generate a serving function for a search engine based on the first objective, the second objective, and the outcome prediction.

Abstract: Technologies for generating user activity features for machine learning models on demand are described. In some embodiments, the technologies receive a request for a user activity feature and a request timestamp from a machine learning model. The technologies determine a data access mechanism, a time window determined based on the request timestamp, and a feature computation algorithm. Using the data access mechanism, the technologies retrieve, from a real-time data store, event data for events having timestamps within the time window, and attribute data associated with the event data. The technologies compute a user activity feature using the retrieved event data and the retrieved attribute data as inputs to the feature computation algorithm, and provide the computed user activity feature to the machine learning model in response to the request for the activity feature.

Abstract: A method can include determining a first probability that a first member of members of a website will visit the website within a specified time window if the first member is provided an intervention at a specified time, determining a second probability that the first member will visit the website within the specified time window without being provided the intervention, determining a difference between the first and second probability, and in response to determining the difference is greater than a first specified threshold, providing the intervention at the specified time.

Abstract: In some embodiments, a computer system generates a recommendation for a user of an online service based on user actions that have been performed by the user within a threshold amount of time before the generation of the recommendation. For each user action, the computer system determines an intent classification that identifies an activity of the user and that corresponds to different types of user actions, as well as a preference classification that identifies a target of the activity, and then stores these intent and preference classifications as part of indications of the user actions for use in generating different types of recommendations using different types of recommendation models. Additionally, the computer system may use mini-batches of data from an incoming stream of logged data to train an incremental update to one or more recommendation models.

Abstract: A system, a machine-readable storage medium storing instructions, and a computer-implemented method are described herein are directed to a Message Diet Engine that generates a pool of messages for a plurality member accounts of a social network service. Each message being of a respective message type from a plurality of message types and targeted to a specific member account. For each respective member account, the Message Diet Engine selects a minimum number of messages, from the pool of messages, targeted to the respective member account that prompts an expected social network activity target and avoids an expected number of complaints. Based on the selected minimum number of messages for each respective member account, the Message Diet Engine identifies a total minimum number of messages, from the pool of messages, to be sent to the plurality of member accounts that prompts an expected total social network activity target and avoids a total expected number of complaints.

Abstract: A system and method for content generation and targeting using machine learning are provided. In example embodiments, a probability that a user will visit a webpage based on historical data is calculated. A probability that the user will engage with a particular content category based on past user engagement is calculated. In response to the probability of the user engaging with the particular content category being equal to or greater than a first threshold, the content is generated. Further, in response to the probability of the user not visiting a webpage meeting or exceeding a second threshold, the generated content is sent to the user.

Abstract: This disclosure relates to systems and methods that include configuring a machine learning system to train on a plurality of messages, the machine learning system to output an expected number of positive responses and an expected number of negative responses based on an input message, determining a threshold differential and a weight value using responses to the plurality of messages, and sending the input message in response to a differential between the expected number of positive responses and the weight multiplied by the expected number of negative responses being above the threshold differential.

Abstract: This disclosure relates to systems and methods that include configuring a machine learning system to train on a plurality of messages transmitted to target groups of an online social networking service, determining a threshold differential and a weight value using responses to the plurality of messages, and send the input message to the target in response to a differential between the expected number of positive responses and the weight multiplied by the expected number of negative responses being greater than the threshold differential.

Abstract: This disclosure relates to systems and methods for managing multiple messages. In one example, a method includes determining a message transmission frequency threshold for a member of an online social networking service using responses from the member; receiving a message that is to be transmitted to the member; storing the message, without transmitting the message to the member, in a digest of messages for the member; and transmitting the digest to the member in response to a send score for the digest exceeding a send score threshold, the send score calculated using the number of messages in the digest.

Abstract: Machine learning techniques for multi-objective content item selection are provided. In one technique, resource allocation data is stored that indicates, for each campaign of multiple campaigns, a resource allocation amount that is assigned by a central authority. In response to receiving the content request, a subset of the campaigns is identified based on targeting criteria. Multiple scores are generated, each score reflecting a likelihood that a content item of the corresponding campaign will be selected. Based on the scores, a particular campaign from the subset is selected and the corresponding content item transmitted over a computer network to be displayed on a computing device. A resource allocation amount that is associated with the particular campaign is identified. A resource reduction amount associated with displaying the content item of the particular campaign is determined. The particular resource allocation is reduced based on the resource reduction amount.

Abstract: Systems and methods for storing less than a threshold number of media content activity levels for media content objects at an online social networking service, identifying, using the stored media content activities, a threshold number of media content objects associated with a higher number of the media content activities occurring over a recent threshold period of time, receiving an indicator indicating that one of the identified media content objects is unprofessional, and propagating the indicator to each activity that includes the unprofessional media content object.

Abstract: A method can include determining a first probability that a first member of members of a website will visit the website within a specified time window if the first member is provided an intervention at a specified time, determining a second probability that the first member will visit the website within the specified time window without being provided the intervention, determining a difference between the first and second probability, and in response to determining the difference is greater than a first specified threshold, providing the intervention at the specified time.

Abstract: This disclosure relates to systems and methods for managing multiple messages. In one example, a method includes determining a message transmission frequency threshold for a member of an online social networking service using responses from the member; receiving a message that is to be transmitted to the member; storing the message, without transmitting the message to the member, in a digest of messages for the member; and transmitting the digest to the member in response to a send score for the digest exceeding a send score threshold, the send score calculated using the number of messages in the digest.

Abstract: This disclosure relates to systems and methods for managing multiple messages. In one example, a method includes determining a message transmission frequency threshold for a member of an online social networking service using responses from the member; receiving a message that is to be transmitted to the member; storing the message, without transmitting the message to the member, in a digest of messages for the member; and transmitting the digest to the member in response to a send score for the digest exceeding a send score threshold, the send score calculated using the number of messages in the digest.

Abstract: A system and method for content generation and targeting using machine learning are provided. In example embodiments, a probability that a user will visit a webpage based on historical data is calculated. A probability that the user will engage with a particular content category based on past user engagement is calculated. In response to the probability of the user engaging with the particular content category being equal to or greater than a first threshold, the content is generated. Further, in response to the probability of the user not visiting a webpage meeting or exceeding a second threshold, the generated content is sent to the user.

Abstract: A system, a machine-readable storage medium storing instructions, and a computer-implemented method are described herein are directed to a Message Diet Engine that generates a pool of messages for a plurality member accounts of a social network service. Each message being of a respective message type from a plurality of message types and targeted to a specific member account. For each respective member account, the Message Diet Engine selects a minimum number of messages, from the pool of messages, targeted to the respective member account that prompts an expected social network activity target and avoids an expected number of complaints. Based on the selected minimum number of messages for each respective member account, the Message Diet Engine identifies a total minimum number of messages, from the pool of messages, to be sent to the plurality of member accounts that prompts an expected total social network activity target and avoids a total expected number of complaints.

Abstract: This disclosure relates to systems and methods that include configuring a machine learning system to train on a plurality of messages, solving, for a set of input messages, a multi-objective optimization problem to minimize a number of messages to send while satisfying one or more constraints, selecting a random value for one or more message and message recipient pairs in the set of input messages, setting a send constraint for one or more of the pairs using a send threshold for the message in the set and the random value, and sending the message to a recipient for the message in the set in response to the send constraint for the pair being satisfied.

Abstract: This disclosure relates to systems and methods for managing multiple messages. In one example, a method includes determining a message transmission frequency threshold for a member of an online social networking service using responses from the member; receiving a message that is to be transmitted to the member; storing the message, without transmitting the message to the member, in a digest of messages for the member; and transmitting the digest to the member response to a send score for the digest exceeding a send score threshold, the send score calculated using the number of messages in the digest.