Generating attribute preference models based on disparate attribute spectrums

摘要

An attribute correlation system reduces network traffic and processing cycles associated with impromptu item selections by generating attribute preference models based on disparate attribute spectrums. The attribute correlation system deploys the attribute preference models to select individual items from various disparate “candidate item categories.” Generally described, the attribute preference models facilitate analyzing item sets across a wide variety of disparate “candidate” item categories to preemptively identify individual items for a user. In this way, the individual items may be identified and, ultimately, selected for the user even absent any indication that the user has searched for otherwise identified these items or even other items from within the disparate “candidate” item categories. The “candidate” item categories may be determined to be disparate from one another based on a relationship void existing such that predefined relationships are missing between these “candidate” item categories.