Abstract: Technologies for generating dynamic notification content for notification messages using a machine learned model are provided. The disclosed techniques include identifying an event related to a particular user, where the event has a particular notification type that represents a subject type of the event. Based on the particular notification type of the event, a set of candidate headline and call-to-action combinations corresponding to the particular notification type are identified. Using the machine learned model, scores are calculated for each headline and call-to-action combination in the set of candidate headline and call-to-action combinations. One or more particular headline and call-to-action combinations from the set of candidate headline and call-to-action combinations are selected based upon the scores calculated for each combination of the set of candidate headline and call-to-action combinations.

Abstract: Techniques for optimizing content item delivery for installations or activations of a mobile application are provided. In one technique, a machine-learned model is trained based on multiple training instances that individually indicate whether an entity performed a particular action relative to a mobile application. In response to receiving a content item request from a third-party content delivery exchange, it is determined whether a client device that initiated the content item request has activated a particular application. In response to determining that the client device has not activated the particular application, multiple feature values of the content item request are identified. Based on inputting the feature values into the model, a score is generated that indicates a likelihood that an entity of the client device will perform the particular action relative to the particular application. Based on the score, a content item is transmitted over a network to the client device.

Abstract: Techniques of content delivery for HTML content based on a predefined template generated at a content serving service are provided. A request for HTML content is received and a member ID that matches the request is determined to identify a set of campaigns. For each identified campaign, a cache is read to identify respective HTML content. Upon determining that one of the campaigns has corresponding HTML content stored in the cache and that was already generated at the content serving service, a URL is generated based on the request. The HTML content and the URL are sent to a client device. For a campaign that does not have stored HTML content, HTML content for that campaign is generated using a template with a predefined format and content that is specific to the campaign. The template has formatting parameters for the content. The generated HTML content is stored in the cache.

Abstract: Technologies for generating dynamic notification content for notification messages using a machine learned model are provided. The disclosed techniques include identifying an event related to a particular user, where the event has a particular notification type that represents a subject type of the event. Based on the particular notification type of the event, a set of candidate headline and call-to-action combinations corresponding to the particular notification type are identified. Using the machine learned model, scores are calculated for each headline and call-to-action combination in the set of candidate headline and call-to-action combinations. One or more particular headline and call-to-action combinations from the set of candidate headline and call-to-action combinations are selected based upon the scores calculated for each combination of the set of candidate headline and call-to-action combinations.

Abstract: Techniques of content delivery for HTML content based on a predefined template generated at a content serving service are provided. A request for HTML content is received and a member ID that matches the request is determined to identify a set of campaigns. For each identified campaign, a cache is read to identify respective HTML content. Upon determining that one of the campaigns has corresponding HTML content stored in the cache and that was already generated at the content serving service, a URL is generated based on the request. The HTML content and the URL are sent to a client device. For a campaign that does not have stored HTML content, HTML content for that campaign is generated using a template with a predefined format and content that is specific to the campaign. The template has formatting parameters for the content. The generated HTML content is stored in the cache.

Abstract: Techniques for optimizing content item delivery for installations or activations of a mobile application are provided. In one technique, a machine-learned model is trained based on multiple training instances that individually indicate whether an entity performed a particular action relative to a mobile application. In response to receiving a content item request from a third-party content delivery exchange, it is determined whether a client device that initiated the content item request has activated a particular application. In response to determining that the client device has not activated the particular application, multiple feature values of the content item request are identified. Based on inputting the feature values into the model, a score is generated that indicates a likelihood that an entity of the client device will perform the particular action relative to the particular application. Based on the score, a content item is transmitted over a network to the client device.