Abstract: An online concierge system for fraud detection in customer orders fulfilled by a picker. A picker client device, with an installed picker application, sends a first list of items related to a fulfilled customer order. Separately, a transaction log containing a second list of items purchased is received from the retailer's inventory system. These lists are compared to identify any unmatched items. A pretrained fraud detection model, trained on historical data with labeled instances of fraud or non-fraud, is applied to the unmatched items to assess the likelihood of fraud. If this likelihood surpasses a predefined threshold, the item is flagged as a fraudulent instance. This determination is then sent to an auditor client device for further action.

Abstract: An online system receives a completed order of items fulfilled by a picker and a transaction log of the completed order from a retailer where the completed order was fulfilled. The online system compares the completed order of items to the transaction log of the completed order to identify one or more unmatched items. The online system generates, at an auditor client device, a user interface that shows the unmatched items and an option to mark each unmatched item as a fraud instance. The online system receives an indication of a fraud instance for one of the unmatched items from an auditor via the user interface. The online system adds a value of the fraud instance to a fraud total of the picker. If the online system determines that the fraud total for the picker exceeds a threshold, the fraud module deactivates the picker's account.

Abstract: An online concierge system sends an order associated with a customer to a shopper for fulfillment at a store. The order specifies an ordered amount of an item. The online concierge system receives an image of a receipt for the order from the shopper after fulfillment of the order, applies an image processing algorithm to identify the item in the image of the receipt, and identifies a measured quantity within the image. The measured quantity represents an actual amount of the item purchased at the store. The online concierge system determines a difference between the actual amount and the ordered amount of the item, and determines an amount to be charged or reimbursed to the customer based in part on the difference between the actual amount and the ordered amount of the item.

Abstract: A customer places an order of items to be purchased with an online concierge system. The online concierge system provides the order to a picker who shops for the items at a retailer and delivers them. The online concierge system requests an image of a receipt of the order from the picker. The online concierge system performs image processing on the image of the receipt and uses machine learning and optical character recognition to determine the actual amounts purchased of items. The online concierge system charges the customer based on the actual amounts purchased of each item.

Abstract: An online system receives a completed order of items fulfilled by a picker and a transaction log of the completed order from a retailer where the completed order was fulfilled. The online system compares the completed order of items to the transaction log of the completed order to identify one or more unmatched items. The online system generates, at an auditor client device, a user interface that shows the unmatched items and an option to mark each unmatched item as a fraud instance. The online system receives an indication of a fraud instance for one of the unmatched items from an auditor via the user interface. The online system adds a value of the fraud instance to a fraud total of the picker. If the online system determines that the fraud total for the picker exceeds a threshold, the fraud module deactivates the picker's account.

Abstract: A customer places an order of items to be purchased with an online concierge system. The online concierge system provides the order to a picker who shops for the items at a retailer and delivers them. The online concierge system requests an image of a receipt of the order from the picker. The online concierge system performs image processing on the image of the receipt and uses machine learning and optical character recognition to determine the actual amounts purchased of items. The online concierge system charges the customer based on the actual amounts purchased of each item.