Abstract: Machine-learned model scoring techniques for reducing model invocations are provided. In one technique, first values for non-pair-specific interaction features that are associated with a first entity are identified. Second values for pair-specific interaction features that are associated with (a) the first entity and (b) a second entity that is different than the first entity are identified. A machine-learned model that has been trained based on the non-pair-specific interaction features and the pair-specific interaction features generates a first score based on the first values. The machine-learned model also generates a second score based on the first values and the second values. A final score for the first entity-second entity pair is computed based on the first score and the second score. Based on the final score, data about the first entity is transmitted over a computer network to a computing device associated with the second entity.

Abstract: Disclosed are systems, methods, and non-transitory computer-readable media for expanding search queries using query term weighting. A search system receives a search term comprising multiple keywords and executes a search query based on the search term. In response to determining that the number of search results is less than a threshold number, the search system determines, based on historical query reformulation data, weight values for the keywords included in the search term. The weight values indicate a probability that each respective keyword would be removed when reformulating the search term. The search system generates a reformulated search term based on the weight values and executes a second search query based on the reformulated search term. The search system causes presentation of at least a portion of the search results on a client device of the requesting user.

Abstract: Disclosed are systems, methods, and non-transitory computer-readable media for expanding search queries using query term weighting. A search system receives a search term comprising multiple keywords and executes a search query based on the search term. In response to determining that the number of search results is less than a threshold number, the search system determines, based on historical query reformulation data, weight values for the keywords included in the search term. The weight values indicate a probability that each respective keyword would be removed when reformulating the search term. The search system generates a reformulated search term based on the weight values and executes a second search query based on the reformulated search term. The search system causes presentation of at least a portion of the search results on a client device of the requesting user.