Groupon, Inc.

Bytedance Inc.

Jikai Lei

Joaquin Delgado

Roger Henry Castillo

Boris Lerner

Emma Sawin

Alvaro Viloria

Ramesh Maddula

Computing systems, computing apparatuses, computing methods, and computer program products are disclosed for machine learning ranking. An example computing method includes receiving a search query and determining a plurality of machine learning model execution engines based on the search query and a plurality of search result types. The example computing method further includes generating a plurality of subsets of search results based on the search query and the plurality of machine learning model execution engines. The example computing method further includes generating a set of search results comprising at least one search result from each of the plurality of subsets of search results.

Machine learning systems architectures for ranking

Embodiments of the present invention provide methods, systems, apparatuses, and computer program products for extending an action vector. In one embodiment, an apparatus is configured to scan each client action vector cell of the client action vector to identify an empty client action vector cell, the client action vector associated with a client profile; upon identifying an empty client action vector cell, extract an empty client action vector cell device rendered object category; retrieve, from a similarity table, a similarity measure for each of the other device rendered object categories of the plurality of device rendered object categories, the similarity measure being in comparison to the empty client action vector cell device rendered object category; for each of the other device rendered object categories of the plurality of device rendered object categories having a similarity measure above a similarity threshold, extract an action count from the client action vector cell associated with the device rendered object category; compute a similarity action measure for the device rendered object category based at least on the action count and the similarity measure; and compute an action measure for the empty client action vector cell using at least one of the similarity action measures; and increment an action count in the empty client action vector cell based on the action measure.

Method, apparatus, and computer program product for extending an action vector

Growing community of inventors

Foster City, CA, United States of America

Jikai Lei