Abstract: Embodiments of the present disclosure relate to a denticle array. The denticle array includes a substrate and a plurality of denticles coupled to the substrate. Each denticle of the plurality of denticles includes an upper portion and a lower portion. The upper portion includes an upper body. The lower portion includes a lower body. The upper body includes a first prong extending from a front end of the denticle to a rear end of the denticle, a second prong extending from the front end of the denticle to a rear end of the denticle, and a third prong extending from the front end of the denticle to a rear end of the denticle. A first ridge separates the first prong and second prong. A second ridge separates the first prong from the third prong. The first prong has a length greater than the second prong and the third prong.

Abstract: A signature matrix is used to test each online event for inclusion of a user in a pre-generated lookalike audience. Locality Sensitive Hashing is used to compile the signature matrix to dramatically reduce memory storage requirements and processing time for each received online event. A technique of producing incremental signature matrices between generation of the full signature matrix helps to enable near-real time performance in processing each received event to see if a user associated with that event should be added to one of the lookalike audiences pre-generated by advertiser.

Abstract: The disclosed computer-implemented method may include (1) sampling links from an online system, (2) receiving, from a human labeler for each of the links, a label indicating whether the human labeler considers a landing page of the link to be a low-quality webpage, (3) generating a link graph from a crawl of the links, (4) using the link graph to derive a graph-based feature for each of the links, (5) using the label and the graph-based feature of each of the links to train a model configured to predict a likelihood that a link is to a low-quality webpage, (6) identifying content items that are candidates for a content feed of a user, (7) applying the model to the content items to determine a ranking, and (8) displaying the content items in the content feed based on the ranking. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: The disclosed computer-implemented method may include (1) sampling links from an online system, (2) receiving, from a human labeler for each of the links, a label indicating whether the human labeler considers a landing page of the link to be a low-quality webpage, (3) deriving features from a landing page of each of the links, (4) using the label and the features of each of the links to train a model configured to predict a likelihood that a link is to a low-quality webpage, (5) identifying content items that are candidates for a content feed of a user of the online system, (6) applying the model to a link of each of the content items to determine a ranking of the content items, and (7) displaying the content items in the content feed of the user based on the ranking. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: The disclosed computer-implemented method may include (1) sampling links from an online system, (2) receiving, from a human labeler for each of the links, a label indicating whether the human labeler considers a landing page of the link to be a low-quality webpage, (3) generating a link graph from a crawl of the links, (4) using the link graph to derive a graph-based feature for each of the links, (5) using the label and the graph-based feature of each of the links to train a model configured to predict a likelihood that a link is to a low-quality webpage, (6) identifying content items that are candidates for a content feed of a user, (7) applying the model to the content items to determine a ranking, and (8) displaying the content items in the content feed based on the ranking. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: A signature matrix is used to test each online event for inclusion of a user in a pre-generated lookalike audience. Locality Sensitive Hashing is used to compile the signature matrix to dramatically reduce memory storage requirements and processing time for each received online event. A technique of producing incremental signature matrices between generation of the full signature matrix helps to enable near-real time performance in processing each received event to see if a user associated with that event should be added to one of the lookalike audiences pre-generated by advertiser.