Abstract: Systems, apparatuses and methods may provide for technology that identifies a plurality of images associated with a first listing and selects a first image from a plurality of images based on one or more of at least one engagement analysis signal or at least one image analysis signal. The at least one engagement analysis signal is associated with click-through rates of a first plurality of listings. The technology sets the first image as a representative image based on the selection of the first image, wherein the representative image represents the first listing.

Abstract: This disclosure is directed to enabling access to a game instance through a social network system. A client-side player component facilitates communication between a game instance on the client device and a backend server of a social networking system. The communication information can be stored in or retrieved from a social graph of the social networking system. The game instance can be initialized from a social platform of the social networking system, and the game can be played without leaving a social network application.

Abstract: In one embodiments, one or more computer systems receive, from a client device of a user, a request to access content. The computer systems access a plurality of assets representing the content. The computer devices calculate, for each asset, using a deep-learning model, a probability of an interaction by the user upon providing the asset to the user, wherein the deep-learning model is based at least in part on one or more features associated with the user, the asset, or the content. The computer devices selects one of the assets based on the probability. The computer devices send, to the client device, the selected asset.

Abstract: A method may include one or more computing devices receiving an indication that a triggering action has been detected from a client device, identifying one or more notifications associated with the triggering action, wherein the one or more notifications have been stored in a queue prior to receiving the indication that the triggering action has been detected, and, for each of the one or more identified notifications, calculating a click-through probability that a user associated with the client device will interact with the notification, wherein the click-through probability is calculated based at least in part on a period the notification was stored in the queue prior to receiving the indication that the of the triggering action has been detected, and determining whether the calculated click-through probability satisfies a threshold and sending, in response to determining that the calculated click-through probability satisfies the threshold, the identified notification to the client device.

Abstract: This disclosure is directed to enabling access to a game instance through a social network system. A client-side player component facilitates communication between a game instance on the client device and a backend server of a social networking system. The communication information can be stored in or retrieved from a social graph of the social networking system. The game instance can be initialized from a social platform of the social networking system, and the game can be played without leaving a social network application.

Abstract: A method may include one or more computing devices receiving an indication that a triggering action has been detected from a client device, identifying one or more notifications associated with the triggering action, wherein the one or more notifications have been stored in a queue prior to receiving the indication that the triggering action has been detected, and, for each of the one or more identified notifications, calculating a click-through probability that a user associated with the client device will interact with the notification, wherein the click-through probability is calculated based at least in part on a period the notification was stored in the queue prior to receiving the indication that the of the triggering action has been detected, and determining whether the calculated click-through probability satisfies a threshold and sending, in response to determining that the calculated click-through probability satisfies the threshold, the identified notification to the client device.

Abstract: This disclosure is directed to enabling access to a game instance through a social network system. A client-side player component facilitates communication between a game instance on the client device and a backend server of a social networking system. The communication information can be stored in or retrieved from a social graph of the social networking system. The game instance can be initialized from a social platform of the social networking system, and the game can be played without leaving a social network application.

Abstract: In one embodiment, a method includes one or more computing devices detecting a triggering action by a user of a social-networking system, wherein the detecting includes receiving information about the triggering action from a client device associated with the user and accessing a queue including multiple notifications. The method also includes, for each of one or more of the notifications, calculating using a machine-learning model, a click-through probability that the user will interact with the notification upon display of the notification, wherein the machine-learning model is based at least in part on one or more features associated with the user or the notification, determining whether the click-through probability satisfies a threshold, and if the click-through probability satisfies the threshold, then sending the notification to the client device associated with the user for display, else, removing the notification from the queue.

Abstract: In one embodiment, a method includes one or more computing devices identifying multiple applications associated with a social-networking system based at least in part on social-networking information for a user associated with the social-networking system. The method also includes calculating, using a machine-learning model and for each of the identified applications, a score based at least in part on a click-through probability that the user will interact with the application upon display of a selectable representation associated with the application, where the machine-learning model is based at least in part on one or more features associated with the user or the application. The method also includes sending, to a client device of the user for display, information to present a selectable representation associated with each of one or more of the identified applications based at least in part on the score for the application.

Abstract: This disclosure is directed to enabling access to a game instance through a social network system. A client-side player component facilitates communication between a game instance on the client device and a backend server of a social networking system. The communication information can be stored in or retrieved from a social graph of the social networking system. The game instance can be initialized from a social platform of the social networking system, and the game can be played without leaving a social network application.

Abstract: In one embodiment, a method includes one or more computing devices identifying multiple applications associated with a social-networking system based at least in part on social-networking information for a user associated with the social-networking system. The method also includes calculating, using a machine-learning model and for each of the identified applications, a score based at least in part on a click-through probability that the user will interact with the application upon display of a selectable representation associated with the application, where the machine-learning model is based at least in part on one or more features associated with the user or the application. The method also includes sending, to a client device of the user for display, information to present a selectable representation associated with each of one or more of the identified applications based at least in part on the score for the application.

Abstract: In one embodiments, one or more computer systems receive, from a client device of a user, a request to access content. The computer systems access a plurality of assets representing the content. The computer devices calculate, for each asset, using a deep-learning model, a probability of an interaction by the user upon providing the asset to the user, wherein the deep-learning model is based at least in part on one or more features associated with the user, the asset, or the content. The computer devices selects one of the assets based on the probability. The computer devices send, to the client device, the selected asset.

Abstract: In one embodiment, a method includes one or more computing devices detecting a triggering action by a user of a social-networking system, wherein the detecting includes receiving information about the triggering action from a client device associated with the user and accessing a queue including multiple notifications. The method also includes, for each of one or more of the notifications, calculating using a machine-learning model, a click-through probability that the user will interact with the notification upon display of the notification, wherein the machine-learning model is based at least in part on one or more features associated with the user or the notification, determining whether the click-through probability satisfies a threshold, and if the click-through probability satisfies the threshold, then sending the notification to the client device associated with the user for display, else, removing the notification from the queue.