Abstract: Methods, systems, and apparatus including computer programs encoded on a computer storage medium, for retrieving image search results using embedding neural network models. In one aspect, an image search query is received. A respective pair numeric embedding for each of a plurality of image-landing page pairs is determined. Each pair numeric embedding is a numeric representation in an embedding space. An image search query embedding neural network processes features of the image search query and generates a query numeric embedding. The query numeric embedding is a numeric representation of the image search query in the same embedding space. A subset of the image-landing page pairs having pair numeric embeddings that are closest to the query numeric embedding of the image search query in the embedding space are identified as first candidate image search results.

Abstract: Methods, systems, and apparatus including computer programs encoded on a computer storage medium, for retrieving image search results using embedding neural network models. In one aspect, an image search query is received. A respective pair numeric embedding for each of a plurality of image-landing page pairs is determined. Each pair numeric embedding is a numeric representation in an embedding space. An image search query embedding neural network processes features of the image search query and generates a query numeric embedding. The query numeric embedding is a numeric representation of the image search query in the same embedding space. A subset of the image-landing page pairs having pair numeric embeddings that are closest to the query numeric embedding of the image search query in the embedding space are identified as first candidate image search results.

Abstract: Methods, systems, and apparatus including computer programs encoded on a computer storage medium, for retrieving image search results using embedding neural network models. In one aspect, an image search query is received. A respective pair numeric embedding for each of a plurality of image-landing page pairs is determined. Each pair numeric embedding is a numeric representation in an embedding space. An image search query embedding neural network processes features of the image search query and generates a query numeric embedding. The query numeric embedding is a numeric representation of the image search query in the same embedding space. A subset of the image-landing page pairs having pair numeric embeddings that are closest to the query numeric embedding of the image search query in the embedding space are identified as first candidate image search results.

Abstract: Methods, systems, and apparatus including computer programs encoded on a computer storage medium, for ranking image search results using machine learning models. In one aspect, a method includes receiving an image search query from a user device; obtaining a plurality of candidate image search results; for each of the candidate image search results: processing (i) features of the image search query and (ii) features of the respective image identified by the candidate image search result using an image search result ranking machine learning model to generate a relevance score that measures a relevance of the candidate image search result to the image search query; ranking the candidate image search results based on the relevance scores; generating an image search results presentation; and providing the image search results for presentation by a user device.

Abstract: A system, method, and computer-readable medium are disclosed that include a database, a website hosting module, a search engine module, and a category display module. The database stores a hierarchy of categories for categorizing products for sale and product records associated with the hierarchy. A search query is received from a user device and a list of product records responsive to the search query is received. A list of dominant records is identified for the product records and a number of top-level categories is identified for the dominant records. A modified hierarchy of categories is identified based on the number of top-level categories and the modified hierarchy is displayed in a navigation portion of a webpage and is usable to filter the list of product records responsive to the search query.

Abstract: A smart coupon-delivery system provides targeted coupons to a user using a criteria-encoded message received from a coupon server. The criteria-encoded message is generated by the coupon server from a behavior-criteria vector that indicates criteria for selecting a recipient of a digital coupon. The system then generates a user-behavior vector to indicate one or more behavior patterns of an end-user, and encodes the user-behavior vector to produce a behavior-encoded message. The system then determines whether the end-user is eligible to receive the digital coupon based on the criteria-encoded message and the behavior-encoded message. If the system determines that the end-user is eligible, the system presents the digital coupon to the end-user.

Abstract: A recommender system can generate a predicted item rating for one user by performing collaborative filtering on item ratings from other users. The recommender system can include a client device that interfaces with a server to obtain a predicted item rating for a local user. The client device can generate a standardized ratings vector for the user, and computes a group identifier for the user based on the standardized ratings vector. The system also generates a noisy ratings vector for the local user, and sends a user-ratings snapshot to a recommendation server that includes the group identifier and the noisy ratings vector. The recommender system can also include the recommendation server that generates a predicted item rating for the user by performing collaborative filtering on ratings vectors from a plurality of other users that belong to the same ratings group.

Abstract: A smart coupon-delivery system provides targeted coupons to a user using a criteria-encoded message received from a coupon server. The criteria-encoded message is generated by the coupon server from a behavior-criteria vector that indicates criteria for selecting a recipient of a digital coupon. The system then generates a user-behavior vector to indicate one or more behavior patterns of an end-user, and encodes the user-behavior vector to produce a behavior-encoded message. The system then determines whether the end-user is eligible to receive the digital coupon based on the criteria-encoded message and the behavior-encoded message. If the system determines that the end-user is eligible, the system presents the digital coupon to the end-user.

Abstract: A recommender system can generate a predicted item rating for one user by performing collaborative filtering on item ratings from other users. The recommender system can include a client device that interfaces with a server to obtain a predicted item rating for a local user. The client device can generate a standardized ratings vector for the user, and computes a group identifier for the user based on the standardized ratings vector. The system also generates a noisy ratings vector for the local user, and sends a user-ratings snapshot to a recommendation server that includes the group identifier and the noisy ratings vector. The recommender system can also include the recommendation server that generates a predicted item rating for the user by performing collaborative filtering on ratings vectors from a plurality of other users that belong to the same ratings group.