Generic card feature extraction based on card rendering as an image

An apparatus, comprising:

• a processor;
• and
• a memory, at least one of the processor or the memory being configured to:
• provide a content item for presentation via a client device associated with a user;
• provide a second content item for presentation via at least one of the client device or a second client device associated with the user;
• responsive to processing an indication of user interaction with the content item and a second indication of user interaction with the second content item, update a computer-generated model based, at least in part, on a feature of both the content item and the second content item;
• provide a third content item for presentation via at least one of the client device or the second client device;
• responsive to processing an indication of a lack of user interaction with the third content item, update the computer-generated model based, at least in part, on one or more features of the third content item;
• and
• provide, for presentation via at least one of the client device or the second client device, one or more content items using the computer-generated model.

A computer program product comprising one or more non-transitory computer-readable media having computer program instructions stored therein, the computer program instructions being configured such that, when executed by one or more computing devices, the computer program instructions cause the one or more computing devices to:

• provide a first set of content items for presentation via a client device associated with a user;
• responsive to processing an indication of user interaction with a content item of the first set of content items, update a computer-generated model based, at least in part, on one or more features of the content item;
• provide, for presentation via at least one of the client device or a second client device associated with the user, a second set of content items using the computer-generated model;
• provide a third set of content items for presentation via at least one of the client device or the second client device;
• and
• responsive to processing an indication of a lack of user interaction with a second content item of the third set of content items, update the computer-generated model based, at least in part, on one or more features of the second content item.