Abstract: An online concierge system identifies a set of attributes of one or more future time periods and accesses a machine learning model trained to predict a set of working hours for a picker during a future time period, in which the set of working hours describes an availability of the picker to service orders placed with the online concierge system. The online concierge system then applies the machine learning model to the set of attributes to predict the set of working hours for the picker during the future time periods and stores the predicted set of working hours for the picker during the future time periods.

Abstract: An online system receives information describing an order placed by a user of the online system and a set of contextual features associated with servicing the order. The online system also retrieves a set of user features associated with the user. The online system accesses a machine learning model trained to predict a tip amount the user is likely to provide for servicing the order and applies the machine learning model to a set of inputs, in which the set of inputs includes the information describing the order, the set of user features, and the set of contextual features. The online system then determines a suggested tip amount for servicing the order based on the predicted tip amount.

Abstract: An online concierge system compensates pickers who fulfill orders including one or more items based in part on weights of the items included in an order. Because the online concierge system does not physically possess the items that are obtained, the online concierge system cannot directly weigh the items and weights specified for items in a catalog from a retailer may be inaccurate. To more accurately determine weights of items, the online concierge system trains a weight prediction model to estimate an item's weight from attributes of the item and uses the output of the weight prediction model to determine compensation to a picker. The weight prediction model may output a predicted weight of an item or a classification of the item as heavy or light. Where discrepancies are found between a predicted weight and the catalog weight of an item, additional information about the item is obtained.

Abstract: An online system receives information describing an order placed by a user of the online system and a set of contextual features associated with servicing the order. The online system also retrieves a set of user features associated with the user. The online system accesses a machine learning model trained to predict a tip amount the user is likely to provide for servicing the order and applies the machine learning model to a set of inputs, in which the set of inputs includes the information describing the order, the set of user features, and the set of contextual features. The online system then determines a suggested tip amount for servicing the order based on the predicted tip amount.

Abstract: An online concierge system receives information describing the progress of a picker servicing a batch of existing orders and predicts a first likelihood the picker will finish servicing the batch within a threshold amount of time based on the picker's progress and information describing the batch. If the first likelihood exceeds a threshold likelihood, the system accesses a machine learning model trained to predict a second likelihood the picker will accept a batch of new orders for servicing while servicing the batch of existing orders. The system applies the model to inputs including a set of attributes of the picker and the picker's progress to predict the second likelihood. The system matches batches of new orders with pickers based on the second likelihood and sends one or more requests to service one or more batches matched with the picker to a client device associated with the picker.

Abstract: An online concierge system receives information describing the progress of a picker servicing a batch of existing orders and a service request for an order. The system identifies picker attributes of the picker and order attributes of the order and each existing order of the set and accesses a machine learning model trained to predict a likelihood the picker will accept an add-on request to add the order to the batch of existing orders. To predict the likelihood, the system applies the model to the picker attributes, the progress of the picker, and the order attributes. The system determines a cost associated with sending the add-on request to the picker based on the likelihood and assigns the order to a set of orders based on the cost. The system sends the add-on request to the picker responsive to determining the order is assigned to the batch of existing orders.

Abstract: A concierge system sends batches of orders to pickers that they can review and accept in a batch list on a client device. Each batch in the batch list is presented with a hide option that enables the picker to hide a batch that they do not intend to accept. In response to receiving a hide signal, the system extracts features associated with the batch and stores those features with a negative indication of the picker towards the batch. The hide signal provides the system with a higher quality signal indicating the picker's negative intent regarding an order, as compared to simply ignoring the order in favor of fulfilling another order. This higher quality signal is then used to train models to better predict events related to the pickers' acceptance of orders, such as for ranking orders for pickers or for predicting fulfillment times.