Abstract: An online system receives a search query from a client device associated with a user and queries a database including item data for a set of items matching the query, in which the set of items is at a retailer location associated with a retailer type and each item is associated with an item category. For each item of the set, a machine learning model is applied to predict a probability of conversion for the user and item and a score is computed based on an expected value, in which the expected value is based on a value associated with the item and the probability. The score for each item is boosted based on the item category, retailer type, or a user segment that is based on the user's historical order data. The items are ranked based on the boosted scores and the ranking is sent to the client device.

Abstract: An online concierge system generates a graph connecting items with attributes of the items and other items. Hence, the graph includes nodes corresponding to attributes and nodes corresponding to items, with an item connected to attributes of the item in the graph. Example attributes include a brand, a category, a department, or any other suitable information about the item. When the online concierge system receives a search query to identify one or more items from a customer, the online concierge system parses the search query into combinations of terms and compares different combinations of terms to the graph to determine connections between different combinations of terms in the graph. Based on measures of connectedness between combinations of terms and connections in the graph, items are identified from one or more combinations of terms. Information about the identified items is presented to the customer.

Abstract: An online concierge system generates an item graph connecting item nodes with attribute nodes of the items. When the online concierge system receives a search query to identify one or more items from a customer, the online concierge system parses the search query into combinations of terms and identifies item nodes and attribute nodes related to the search query. The online concierge system may determine that no item nodes meet presentation criteria. The online concierge system may determine that a reformulated search query has a higher conversion probability than the search query received from the customer. The online concierge system reformulates the search query. The online concierge system selects item nodes as search results. The online concierge system transmits the search results to the customer.

Abstract: An online concierge system generates a graph connecting items with attributes of the items and other items. Hence, the graph includes nodes corresponding to attributes and nodes corresponding to items, with an item connected to attributes of the item in the graph. Example attributes include a brand, a category, a department, or any other suitable information about the item. When the online concierge system receives a search query to identify one or more items from a customer, the online concierge system parses the search query into combinations of terms and compares different combinations of terms to the graph to determine connections between different combinations of terms in the graph. Based on measures of connectedness between combinations of terms and connections in the graph, items are identified from one or more combinations of terms. Information about the identified items is presented to the customer.

Abstract: An online concierge system generates an item graph connecting item nodes with attribute nodes of the items. Example attributes include a brand, a category, a department, or any other suitable information about the item. When the online concierge system receives a search query to identify one or more items from a customer, the online concierge system parses the search query into combinations of terms and identifies item nodes and attribute nodes related to the search query. The online concierge system identifies item nodes and attribute nodes that are likely to result in a conversion. Information about the identified nodes is presented to the customer. The customer may select an item node to purchase the item, or an attribute node to execute a new search query based on terms associated with the attribute node.

Abstract: An online system provides options for selection by a user. The online system receives a query entered on a client device. The online system queries an item database to retrieve a set of items related to the query and assigns each item to a product category in a predefined taxonomy that maps items to product categories. The online system inputs each item into a prediction model trained to predict a probability that an item is available at a warehouse location. The online system determines that a first product category has low availability based on predicted probabilities for items in the first product category. Responsive to determining that a first product category has low availability, the online system generates a generic item for the first product category and sends a list of items including the generic item to the client device for display responsive to the query.

Abstract: An online concierge shopping system identifies recipes to users to encourage them to include items from the recipes in orders. The online concierge system maintains user embeddings for users and recipe embeddings for recipes. For users who have not placed orders, recipes are recommended based on global user interactions with recipes. Users who have previously ordered items from recipes are suggested recipes selected based on a similarity of their user embedding to recipe embeddings. Users who have purchased items but not from recipes are compared to a set of similar users based on the user embeddings, and recipes with which users of the set of similar users interacted are used for identifying recipes to the users. A recipe graph may be maintained by the online concierge system to identify similarities between recipes for expanding candidate recipes to suggest to users.

Abstract: An online system provides options for selection by a user. The online system receives a query entered on a client device. The online system queries an item database to retrieve a set of items related to the query and assigns each item to a product category in a predefined taxonomy that maps items to product categories. The online system inputs each item into a prediction model trained to predict a probability that an item is available at a warehouse location. The online system determines that a first product category has low availability based on predicted probabilities for items in the first product category. Responsive to determining that a first product category has low availability, the online system generates a generic item for the first product category and sends a list of items including the generic item to the client device for display responsive to the query.

Abstract: An online concierge system maintains various items and an item embedding for each item. When the online concierge system receives a query for retrieving one or more items, the online concierge system generates an embedding for the query. The online concierge system trains a machine-learned model to determine a measure of relevance of an embedding for a query to item embeddings by generating training data of examples including queries and items with which users performed a specific interaction. The online concierge system generates a subset of the training data including examples satisfying one or more criteria and further trains the machine-learned model by application to the examples of the subset of the training data and stores parameters resulting from the further training as parameters of the machine-learned model.

Abstract: An online concierge system receives a search query from a client device. The online concierge system identifies a set of matching items from an item database. The matching items correspond to the received search query. The online concierge system obtains, from a hierarchical item taxonomy, a category label for each matching item. The item taxonomy relates each item in the item database to one of a plurality of category labels. The online concierge system groups the matching items by the category labels for each of the matching items into one or more groups. The online concierge system generates instructions for a user interface. The user interface includes a scrollable list of one or more carousels. Each carousel includes a scrollable list of a group of the one or more groups. The online concierge system sends the instructions of the user interface to the client device for display.

Abstract: An online system maintains item embeddings for items. As a number of items maintained by the online system increases, maintaining a single index of the item embeddings is increasingly difficult. To increase scalability, the online system partitions item embeddings into multiple indices, with each index corresponding to a value of a specific attribute maintained by the online system for items. For example, an online system generates indices that each correspond to a different warehouse offering items. To expedite retrieval of item embeddings, the online system allocates each index to one of a number of shards. When the online system receives a query, the online system determines an embedding for the query and retrieves an index from a shard based on metadata received with the query. Based on distances between the query for the embedding and the item embeddings in the retrieved index, the online system selects one or more items.

Abstract: An online system maintains various items and maintains values for different attributes of the items, as well as an item embedding for each item. When the online system receives a query for retrieving one or more items, the online system generates an embedding for the query. Based on measures of similarity between the embedding for the query and item embeddings, the online system selects a set of items. The online system identifies a specific attribute of items and generates a whitelist of values for the specific attribute based on measures of similarity between item embeddings for items in the selected set and the embedding for the query. The online system removes items having values for the selected attribute outside of the whitelist of values from the selected set of items to identify items more likely to be relevant to the query.

Abstract: An online system leverages stored interactions with items made by users after the online system received queries to determine display of items satisfying the query. For example, the online system trains a model to predict a likelihood of a user performing an interaction with an item displayed after a query was received. As different items receive different amounts of interaction from users, limited historical interaction with certain items may limit accuracy of the model. The online system generates embeddings for previously received queries and uses measures of similarity between embeddings for queries to generate clusters of queries. Previous interactions with queries in a cluster are combined, with the combined data being used for determining display of items in response to a query.

Abstract: An online concierge shopping system identifies recipes to users to encourage them to include items from the recipes in orders. The online concierge system maintains user embeddings for users and recipe embeddings for recipes. For users who have not placed orders, recipes are recommended based on global user interactions with recipes. Users who have previously ordered items from recipes are suggested recipes selected based on a similarity of their user embedding to recipe embeddings. Users who have purchased items but not from recipes are compared to a set of similar users based on the user embeddings, and recipes with which users of the set of similar users interacted are used for identifying recipes to the users. A recipe graph may be maintained by the online concierge system to identify similarities between recipes for expanding candidate recipes to suggest to users.

Abstract: An online concierge system generates an item graph connecting item nodes with attribute nodes of the items. Example attributes include a brand, a category, a department, or any other suitable information about the item. When the online concierge system receives a search query to identify one or more items from a customer, the online concierge system parses the search query into combinations of terms and identifies item nodes and attribute nodes related to the search query. The online concierge system identifies item nodes and attribute nodes that are likely to result in a conversion. Information about the identified nodes is presented to the customer. The customer may select an item node to purchase the item, or an attribute node to execute a new search query based on terms associated with the attribute node.

Abstract: To simplify retrieval of items from a database that at least partially satisfy a received query, an online concierge system trains a model that outputs scores for items from the database without initially retrieving items for evaluation by the model. The online concierge system pre-trains the model using natural language inputs corresponding to items from the database, with a natural language input including masked words that the model is trained to predict. Subsequently, the model is refined using multi-task training where a task is trained to predict scores for items from the received query. The online concierge system selects items for display in response to the received query based on the predicted scores.

Abstract: An online concierge system improves on methods for presenting content to users. The online concierge system generates a user embedding for a user and recipe embeddings for candidate recipes. The online concierge system generates a context embedding by applying a context embedding model to context data received from a user mobile application. The online concierge system calculates an overall score for each candidate recipe based on a user score and a context score. The user score is calculated based on the user embedding and a recipe embedding for the candidate recipe. The context score is calculated based on the generated context embedding and the recipe embedding for the candidate recipe. The online system selects a recipe for presentation to the user based on the overall scores. The online concierge system trains the context embedding model using a loss function that is based on the user score and the context score.

Abstract: An online concierge system generates an item graph connecting item nodes with attribute nodes of the items. Example attributes include a brand, a category, a department, or any other suitable information about the item. When the online concierge system receives a search query to identify one or more items from a customer, the online concierge system parses the search query into combinations of terms and identifies item nodes and attribute nodes related to the search query. The online concierge system identifies item nodes and attribute nodes that are likely to result in a conversion. Information about the identified nodes is presented to the customer. The customer may select an item node to purchase the item, or an attribute node to execute a new search query based on terms associated with the attribute node.

Abstract: An online concierge system displays a search interface to users. The search interface receives s prefix of a search query from a user and determines terms for completing the prefix, with the terms displayed to a user as suggestions via the search interface. The online concierge system determines probabilities of the user adding items corresponding to terms for completing the prefix when different terms are displayed. The online concierge system displays the terms for completing the prefix in an order based on the determined probabilities of including a corresponding item in an order rather than in an order based on likelihoods of the user selecting different terms.

Abstract: An online concierge system suggests recipes to users to encourage them to include items from the recipes in orders. When suggesting a recipe to a user, the online concierge system maps generic item descriptions in a recipe to specific items for sale at a warehouse identified by the user. The online concierge system maintains a recipe store including mappings of generic item descriptions in recipes to specific items. To determine mappings between generic item descriptions and specific items, the online concierge system determines a category from a taxonomy for a generic item description in a recipe and excludes specific items in different categories than the determined category.