Abstract: The present disclosure is directed to determining purchase suggestions for an online shopping concierge platform. In particular, the methods and systems of the present disclosure may receive, from a computing device associated with a customer of an online shopping concierge platform, data indicating one or more interactions of the customer with the online shopping concierge platform; determine, based at least in part on one or more machine learning (ML) models and the data indicating the interaction(s), a likelihood that the customer will purchase a particular item if presented, at a specific time, with a suggestion to purchase the particular item; and generate and communicate data describing a graphical user interface (GUI) comprising at least a portion of a listing of one or more purchase suggestions including the suggestion to purchase the particular item.

Abstract: The present disclosure is directed to determining purchase suggestions for an online shopping concierge platform. In particular, the methods and systems of the present disclosure may receive, from a computing device associated with a customer of an online shopping concierge platform, data indicating one or more interactions of the customer with the online shopping concierge platform; determine, based at least in part on one or more machine learning (ML) models and the data indicating the interaction(s), a likelihood that the customer will purchase a particular item if presented, at a specific time, with a suggestion to purchase the particular item; and generate and communicate data describing a graphical user interface (GUI) comprising at least a portion of a listing of one or more purchase suggestions including the suggestion to purchase the particular item.

Abstract: An online concierge system facilitates ordering, procurement, and delivery of items to a customer from physical retailers based on shared cart recommendations. Based on customer identifying information and other data sources, the online concierge system may recommend prepopulated shared carts that may be of interest to a customer. The prepopulated carts may be associated with other users of the online concierge system or may be associated with specific events, locations, or other metadata. Prepopulated carts may be created by other users that select to share their carts. Additionally, prepopulated carts may be created and shared by retailers, manufacturers, wholesalers, or other stakeholders in the selling of items through the online concierge system. Furthermore, recommended carts may be automatically generated based on machine learning techniques.

Abstract: An online concierge system facilitates ordering, procurement, and delivery of items to a customer from physical retailers based on shared cart recommendations. Based on customer identifying information and other data sources, the online concierge system may recommend prepopulated shared carts that may be of interest to a customer. The prepopulated carts may be associated with other users of the online concierge system or may be associated with specific events, locations, or other metadata. Prepopulated carts may be created by other users that select to share their carts. Additionally, prepopulated carts may be created and shared by retailers, manufacturers, wholesalers, or other stakeholders in the selling of items through the online concierge system. Furthermore, recommended carts may be automatically generated based on machine learning techniques.

Abstract: Different possible candidate routes for efficiently obtaining a set of items at given retailer premises are generated and simulated to estimate degrees of difficulty of the various routes, such as how long they are expected to take. The current conditions can be inferred based on analysis of environment data received from a plurality of devices associated with users shopping for items on the retailer premises, such as location data, camera data, or comments related to the retailer premises. The simulation takes into account current or expected conditions in the environment of the retailer premises, such as obstructions, alternative placements of items, etc. Routes with least degrees of difficulty may be presented to the users shopping for the items so that the users can use the most efficient routes when obtaining the items.

Abstract: A trained computer model for generating an aggregated health score for a business user of an online system. The online system obtains a set of health scores for a set of individual employees of a business user of an online system. The online system accesses a computer model of the online system trained to determine an aggregated health score for the business user. The online system applies the computer model to generate, based at least in part on the set of health scores and content of a set of orders placed by the business user, the aggregated health score for the business user. The online system causes a device of the business user to display a user interface with the aggregated health score.

Abstract: An online concierge system uses images captured for fulfillment of a first order to affect item information of a second order. When a picker fulfills the first order in a physical warehouse, the picker captures an image of the physical warehouse, for example to capture an image of potential replacement items. The online concierge system detects items in the image along with a location of the item in the physical warehouse based on the image. The detected items and respective locations may then be used to modify a second order, for example to route a picker for the second order to updated or alternate locations of the detected items.

Abstract: The present disclosure is directed to determining purchase suggestions for an online shopping concierge platform. In particular, the methods and systems of the present disclosure may receive, from a computing device associated with a customer of an online shopping concierge platform, data indicating one or more interactions of the customer with the online shopping concierge platform; determine, based at least in part on one or more machine learning (ML) models and the data indicating the interaction(s), a likelihood that the customer will purchase a particular item if presented, at a specific time, with a suggestion to purchase the particular item; and generate and communicate data describing a graphical user interface (GUI) comprising at least a portion of a listing of one or more purchase suggestions including the suggestion to purchase the particular item.

Abstract: An online system performs an inference task in conjunction with the model serving system or the interface system to continuously monitor conversations between users and shoppers to determine whether a message sent by a sending party can be automatically responded to rather than prompting the receiving party for a manual response. The online system automatically provides a response to the message without the receiving party's manual involvement. In one or more embodiments, the online system can infer whether a question can be intercepted and/or suggests one or more available answers the sender can consider as feedback without a manual response from the receiver.

Abstract: An online system performs an inference task in conjunction with the model serving system or the interface system to continuously monitor conversations between requesting users and fulfillment users to determine whether the online system can intervene to automatically respond to a message sent by a sending party, rather than prompting the receiving party for a manual reply. Upon inferring that a message can be automatically responded to, the online system automatically provides a response to the message without the receiving party's manual involvement. The online system can further be augmented to classify and reroute certain requesting user or fulfillment user queries that impact an order's end state by intercepting the conversation on behalf of either party and performing one or more automated actions. If the message is action-oriented, the online system may perform one or more automated actions in response to the message.

Abstract: An online concierge system facilitates ordering, procurement, and delivery of items to a customer from physical retailers based on shared cart recommendations. Based on customer identifying information and other data sources, the online concierge system may recommend prepopulated shared carts that may be of interest to a customer. The prepopulated carts may be associated with other users of the online concierge system or may be associated with specific events, locations, or other metadata. Prepopulated carts may be created by other users that select to share their carts. Additionally, prepopulated carts may be created and shared by retailers, manufacturers, wholesalers, or other stakeholders in the selling of items through the online concierge system. Furthermore, recommended carts may be automatically generated based on machine learning techniques.