Abstract: An online system presents content to its users, in which the content includes links that launch a messaging application and initiate conversations via the application. The system receives information indicating that negative experiences occurred during the conversations and may use this information and attributes of entities participating in the conversations to train a model to predict a likelihood of an occurrence of a negative experience. Upon determining an opportunity to present a user with a link that launches the application and initiates a potential conversation with an entity via the application, the system applies the model to predict a likelihood of an occurrence of the negative experience by the user during the potential conversation based on the entity's attributes. Based on the predicted likelihood, the system adjusts a value associated with presenting the link and passes the adjusted value to a process that selects content for presentation to the user.

Abstract: An online system presents content to its users, in which the content includes links that launch a messaging application and initiate conversations via the application. The system receives information indicating that negative experiences occurred during the conversations and may use this information and attributes of entities participating in the conversations to train a model to predict a likelihood of an occurrence of a negative experience. Upon determining an opportunity to present a user with a link that launches the application and initiates a potential conversation with an entity via the application, the system applies the model to predict a likelihood of an occurrence of the negative experience by the user during the potential conversation based on the entity's attributes. Based on the predicted likelihood, the system adjusts a value associated with presenting the link and passes the adjusted value to a process that selects content for presentation to the user.

Abstract: A request to communicate a message to a business entity via an online messaging application is received from a user of the online messaging application. An intent of the user is extracted by applying a set of natural language processing techniques to the message and a set of template responses associated with the business entity is retrieved. The intent of the user is mapped to a template response included among the set of template responses and the template response is sent for display to the user. The template response may be communicated to an administrator of an account associated with the business entity and sent for display to the user in response to receiving a request from the administrator to do so. One or more of these steps may be performed at the online messaging application or at a client device associated with the user or the business entity.

Abstract: An online system receives a content item from a content provider, the content item having a bid price and including a link to a messaging application. The link is configured to initiate a direct message in the messaging application between the content provider and a user who interacts with the content item. The online system receives a request for content items from a target user and determines a compatibility score between the target user and the content item based on one or more sets of criteria. A first set of criteria indicates a compatibility between the user and the messaging application. The online system determines a subsidy for the content item based on the compatibility score. The online system adjusts the bid price with the determined subsidy to determine an auction price and includes the content item with the auction price in a selection process for presentation to the user of the online system.

Abstract: A method for conversion attribution. The method includes obtaining a first identifier associated with a first device, obtaining a second identifier associated with a second device, bridging the first identifier and the second identifier based on a determination, made by a probabilistic classifier, that the first identifier and the second identifier are associated with a common user, and attributing, using the bridge, a conversion on a website accessed using the second device.

Abstract: A method for conversion attribution. The method includes obtaining a first identifier associated with a first device, obtaining a second identifier associated with a second device, bridging the first identifier and the second identifier based on a determination, made by a probabilistic classifier, that the first identifier and the second identifier are associated with a common user, and attributing, using the bridge, a conversion on a website accessed using the second device.

Abstract: An electronic shopping system, such as an ecommerce retail website, is constructed and programmed to provide online shoppers with the ability to create and manage multiple configurable item orders contemporaneously within a single customer account. Each item in an item order is associated with a “purchase status” which can, in addition to other discrete adjustments, be toggled between “active” and “inactive” states at or before checkout. Each item order is itself configurable in respect of delivery address, payment source, frequency, and schedule. Orders and settings are saved within the customer's account to be recalled, reviewed, refined (if desired), and executed at checkout.

Abstract: Systems, methods, and non-transitory computer readable media providing shared online shopping lists and/or carts among users are disclosed. The method includes receiving a primary virtual shopping cart containing related items generated by a first user. A database entry for the primary shopping cart is created and correlated with a shopping cart identifier in response to a user request. The database entry includes one or more keywords associated with the first user of the primary virtual shopping cart. A query is received from a second user, and a list of primary virtual shopping carts is provided to the second user based on relevancy to the query. In response to a request by the second user, the contents of a selected primary virtual shopping cart is duplicated in a secondary virtual shopping cart associated with the second user.

Abstract: When an online system receives a request to present content items to a user, a content selection system included in the online system selects content items for presentation to the user. A feedback control mechanism communicates with each computing device of the content selection system to determine the latency period and the CPU utilization of each computing device. The feedback control mechanism also determines a target latency period and a target CPU utilization in which content items are selected. By comparing the latency period of each computing device to the target latency period and the CPU utilization to the target CPU utilization, an amount of information to be evaluated by each computing device is determined based on the comparisons.

Abstract: A method for conversion attribution. The method includes obtaining a first identifier associated with a first device, obtaining a second identifier associated with a second device, bridging the first identifier and the second identifier based on a determination, made by a probabilistic classifier, that the first identifier and the second identifier are associated with a common user, and attributing, using the bridge, a conversion on a website accessed using the second device.

Abstract: Systems, methods, and non-transitory computer readable media providing shared online shopping lists and/or carts among users are disclosed. The method includes receiving a primary virtual shopping cart containing related items generated by a first user. A database entry for the primary shopping cart is created and correlated with a shopping cart identifier in response to a user request. The database entry includes one or more keywords associated with the first user of the primary virtual shopping cart. A query is received from a second user, and a list of primary virtual shopping carts is provided to the second user based on relevancy to the query. In response to a request by the second user, the contents of a selected primary virtual shopping cart is duplicated in a secondary virtual shopping cart associated with the second user.

Abstract: Systems, methods, and non-transitory computer readable media providing shared online shopping lists and/or carts among users are disclosed. The method includes receiving a primary virtual shopping cart containing related items generated by a first user. A database entry for the primary shopping cart is created and correlated with a shopping cart identifier in response to a user request. The database entry includes one or more keywords associated with the first user of the primary virtual shopping cart. A query is received from a second user, and a list of primary virtual shopping carts is provided to the second user based on relevancy to the query. In response to a request by the second user, the contents of a selected primary virtual shopping cart is duplicated in a secondary virtual shopping cart associated with the second user.

Abstract: An electronic shopping system, such as an ecommerce retail website, is constructed and programmed to provide online shoppers with the ability to create and manage multiple configurable item orders contemporaneously within a single customer account. Each item in an item order is associated with a “purchase status” which can, in addition to other discrete adjustments, be toggled between “active” and “inactive” states at or before checkout. Each item order is itself configurable in respect of delivery address, payment source, frequency, and schedule. Orders and settings are saved within the customer's account to be recalled, reviewed, refined (if desired), and executed at checkout.

Abstract: An electronic shopping system, such as an ecommerce retail website, is constructed and programmed to provide online shoppers with the ability to create and manage multiple configurable item orders contemporaneously within a single customer account. Each item in an item order is associated with a “purchase status” which can, in addition to other discrete adjustments, be toggled between “active” and “inactive” states at or before checkout. Each item order is itself configurable in respect of delivery address, payment source, frequency, and schedule. Orders and settings are saved within the customer's account to be recalled, reviewed, refined (if desired), and executed at checkout.

Abstract: Provided are a retail checkout system and method. A customer record includes registered identification information related to a store customer. An input device receives unique customer identification information from a purchaser card of the store customer. A customer identification analyzer verifies that the received unique customer identification information is included in the registered identification information of the customer record. An order linking module associates purchase data with the unique customer identification information of the purchaser card. A customer record processor updates the customer record to include the purchase data.

Abstract: Systems and methods for improving the time and cost to calculate connected components in a distributed graph are disclosed. One method includes reducing a quantity of map-reduce rounds used to determine a cluster assignment for a node in a large distributed graph by alternating between two hashing functions in the map stage of a map-reduce round and storing the cluster assignment for the node in a memory. Another method includes reducing a quantity of messages sent during map-reduce rounds by performing a predetermined quantity of rounds to generate, for each node, a set of potential cluster assignments, generating a data structure in memory to store a mapping between each node and its potential cluster assignment, and using the data structure during remaining map-reduce rounds, wherein the remaining map-reduce rounds do not send messages between nodes. The method can also include storing the cluster assignment for the node in a memory.

Abstract: A real-time messaging platform allows advertiser accounts to pay to insert candidate messages into the message streams requested by account holders. To accommodate multiple advertisers, the messaging platform controls an auction process that determines which candidate messages are selected for inclusion in a requested account holder's message stream. Selection is based on a bid for the candidate message, the message stream that is requested, and a variety of other factors that vary depending upon the implementation. The process for selection of candidate messages generally includes the following steps, though any given step may be omitted or combined into another step in a different implementation: targeting, filtering, prediction, ranking, and selection.

Abstract: Systems, methods, and non-transitory computer readable media providing shared online shopping lists and/or carts among users are disclosed. The method includes receiving a primary virtual shopping cart containing related items generated by a first user. A database entry for the primary shopping cart is created and correlated with a shopping cart identifier in response to a user request. The database entry includes one or more keywords associated with the first user of the primary virtual shopping cart. A query is received from a second user, and a list of primary virtual shopping carts is provided to the second user based on relevancy to the query. In response to a request by the second user, the contents of a selected primary virtual shopping cart is duplicated in a secondary virtual shopping cart associated with the second user.

Abstract: An electronic shopping system, such as an ecommerce retail website, is constructed and programmed to provide online shoppers with the ability to create and manage multiple configurable item orders contemporaneously within a single customer account. Each item in an item order is associated with a “purchase status” which can, in addition to other discrete adjustments, be toggled between “active” and “inactive” states at or before checkout. Each item order is itself configurable in respect of delivery address, payment source, frequency, and schedule. Orders and settings are saved within the customer's account to be recalled, reviewed, refined (if desired), and executed at checkout.

Abstract: Systems and methods for improving the time and cost to calculate connected components in a distributed graph are disclosed. One method includes reducing a quantity of map-reduce rounds used to determine a cluster assignment for a node in a large distributed graph by alternating between two hashing functions in the map stage of a map-reduce round and storing the cluster assignment for the node in a memory. Another method includes reducing a quantity of messages sent during map-reduce rounds by performing a predetermined quantity of rounds to generate, for each node, a set of potential cluster assignments, generating a data structure in memory to store a mapping between each node and its potential cluster assignment, and using the data structure during remaining map-reduce rounds, wherein the remaining map-reduce rounds do not send messages between nodes. The method can also include storing the cluster assignment for the node in a memory.