Abstract: An online concierge system selects picker expertise tags that showcase abilities or experiences of pickers that fulfill orders for the system. The online concierge system establishes a set of user-order cohorts based on characteristics of orders and users placing the orders. When an order is received, the online concierge system identifies a relevant user-order cohort and applies a trained model to predict, in the context of the user-order cohort, the performance of various candidate picker expertise tags applicable to the order. The trained model may be generated via a training and testing process in which different picker expertise tags are tested in the context of a user-order cohort, and performance metrics are observed to learn which picker expertise tags perform best in the context of a user-order cohort.

Abstract: An online system receives orders including items from customers and allocates the orders to pickers. A picker obtains items included in an order from a customer and delivers the items to the customer to fulfill the order. To provide encouragement for pickers fulfilling orders, the online system generates a highlight reel of accomplishments of a picker fulfilling orders. The online system generates prompts for a generative model, such as a large language model, based on stored information describing order fulfillment by a picker. Content, such as text, generated in response to a prompt by the generative model includes one or more portions of the stored information describing order fulfillment is included in the highlight reel. A template for the highlight reel is selected for the picker, with the template identifying content displayed to the picker and an order in which the content is displayed.

Abstract: An online concierge system selects picker expertise tags that showcase abilities or experiences of pickers that fulfill orders for the system. The online concierge system establishes a set of user-order cohorts based on characteristics of orders and users placing the orders. When an order is received, the online concierge system identifies a relevant user-order cohort and applies a trained model to predict, in the context of the user-order cohort, the performance of various candidate picker expertise tags applicable to the order. The trained model may be generated via a training and testing process in which different picker expertise tags are tested in the context of a user-order cohort, and performance metrics are observed to learn which picker expertise tags perform best in the context of a user-order cohort.

Abstract: An online system receives orders including items from customers and allocates the orders to pickers. A picker obtains items included in an order from a customer and delivers the items to the customer to fulfill the order. To provide encouragement for pickers fulfilling orders, the online system generates a highlight reel of accomplishments of a picker fulfilling orders. The online system generates prompts for a generative model, such as a large language model, based on stored information describing order fulfillment by a picker. Content, such as text, generated in response to a prompt by the generative model includes one or more portions of the stored information describing order fulfillment is included in the highlight reel. A template for the highlight reel is selected for the picker, with the template identifying content displayed to the picker and an order in which the content is displayed.