Fulfilling orders using supply from identified users

A computer program product comprising:

• one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions comprising:
• program instructions to receive a request to purchase an item from a retailer, wherein the request includes location information associated with a buyer;
• program instructions to identify that the item is unavailable from the retailer;
• program instructions to determine, using a machine learning technique that utilizes one or more weights, a plurality of users predicted to have a surplus quantity of the item beyond each respective user's estimated needs at a time of the request, wherein the plurality of users previously purchased the item from the retailer, the determination further based on:
• monitoring previous purchases of the item from the retailer by the plurality of users;
• and
• previous adjustments to the one or more weights in response to inputting previous offers as feedback along with previous responses to at least one previously sent offer to transfer the item;
• program instructions to send an offer to the plurality of users determined, using the machine learning technique, to have the surplus quantity of the item, to transfer the item to the buyer in accordance with the request;
• program instructions to adjust the one or more weights of the machine learning technique, for subsequent determinations of users predicted to have subsequent surplus quantities of the item, based on inputting the offer as feedback along with responses to the offer from the plurality of users, each response indicating whether the offer was accepted by a respective user of the plurality of users;
• program instructions to, responsive to receiving an acceptance of the offer to transfer the item, select at least one accepting user, of the plurality of users, based on geographic proximity of the at least one accepting user to the location information associated with the buyer being closer than other users of the plurality of users;
• and
• program instructions to coordinate fulfillment of the request by the selected at least one accepting user via a transfer of the item from the selected at least one accepting user to the buyer.

A computer system comprising:

• one or more computer processors, one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media for execution by at least one of the one or more computer processors, the program instructions comprising:
• program instructions to receive a request to purchase an item from a retailer, wherein the request includes location information associated with a buyer;
• program instructions to identify that the item is unavailable from the retailer;
• program instructions to determine, using a machine learning technique that utilizes one or more weights, a plurality of users predicted to have a surplus quantity of the item beyond each respective user's estimated needs at a time of the request, wherein the plurality of users previously purchased the item from the retailer, the determination further based on:
• monitoring previous purchases of the item from the retailer by the plurality of users;
• and
• previous adjustments to the one or more weights in response to inputting previous offers as feedback along with previous responses to at least one previously sent offer to transfer the item;
• program instructions to send an offer to the plurality of users determined, using the machine learning technique, to have the surplus quantity of the item, to transfer the item to the buyer in accordance with the request;
• program instructions to adjust the one or more weights of the machine learning technique, for subsequent determinations of users predicted to have subsequent surplus quantities of items the item, based on inputting the offer as feedback along with responses to the offer from the plurality of users, each response indicating whether the offer was accepted by a respective user of the plurality of users;
• program instructions to, responsive to receiving an acceptance of the offer to transfer the item, select at least one accepting user, of the plurality of users, based on geographic proximity of the at least one accepting user to the location information associated with the buyer being closer than other users of the plurality of users;
• and
• program instructions to coordinate fulfillment of the request by the selected at least one accepting user via a transfer of the item from the selected at least one accepting user to the buyer.