Order fulfillment
Systems and methods for the automated fulfillment of orders from a fulfillment network including consumer-facing retail locations. Orders are partitioned into suborders, which are in turn assigned to retail locations based on forecasted demand for the suborder items at the retail locations. The assignment process considers operational data for each retail location such as the number of employees, the inventory of suborder items, shipping rate cards, return policies, business hours, pick decline estimations, etc.
1. A system for fulfilling orders from a fulfillment network comprising a plurality of consumer-facing retail locations, the system comprising at least one computer comprising processing circuitry and memory, the memory storing instructions which, when executed by the processing circuitry, cause the processing circuitry to perform operations comprising:
retrieving inventory information for the plurality of retail locations in the fulfillment network;
receiving a customer order for multiple items;
forecasting demand for each of the multiple items in each of the multiple retail locations;
based at least in part on the inventory information and the forecast demand, partitioning the customer order into multiple suborders and assigning the multiple suborders to multiple respective retail locations of the plurality of retail locations for fulfillment, each suborder comprising at least one of the multiple items; and
transmitting each suborder to the selected retail location for fulfillment.
2. The system of claim 1 , wherein assigning the multiple suborders to the respective retail locations comprises solving a linear programming problem.
3. The system of claim 2 , wherein solving the linear programming problem employs a primal-dual approach with constraints comprising retail location inventory.
4. The system of claim 1 , wherein the demand is forecast based on historical data for the plurality of items and the plurality of retail locations.
5. The system of claim 1 , wherein the inventory information is retrieved on a scheduled basis, and wherein forecasting the demand comprises predicting current inventory for each of the multiple items in each of the plurality of retail locations.
6. The system of claim 1 , forecasting the demand comprises balancing inventory across the multiple retail locations to meet expected demand at the multiple retail locations after fulfillment of the suborders.
7. The system of claim 1 , wherein the customer order comprises an address and a deadline for delivery, and wherein the partitioning and assigning are further based on at least one of delivery time or delivery cost.
8. The system of claim 1 , wherein the inventory information is retrieved as part of retrieving operational data, the operational data further comprising at least one of daily sales reports, staffing records, shipping records, shipping rate cards, return policies, business hours, or pick decline estimation.
9. A method, performed by processing circuitry, for fulfilling orders from a fulfillment network comprising a plurality of consumer-facing retail locations, the method comprising:
retrieving inventory information for the plurality of retail locations in the fulfillment network;
receiving a customer order for multiple items;
forecasting demand for each of the multiple items in each of the multiple retail locations;
based at least in part on the inventory information and the forecast demand, partitioning the customer order into multiple suborders and assigning the multiple suborders to multiple respective retail locations of the plurality of retail locations for fulfillment, each suborder comprising at least one of the multiple items; and
transmitting each suborder to the selected retail location for fulfillment.
10. The method of claim 9 , wherein assigning the multiple suborders to the respective retail locations comprises solving a linear programming problem.
11. The method of claim 10 , wherein solving the linear programming problem employs a primal-dual approach with constraints comprising retail location inventory.
12. The method of claim 9 , wherein the demand is forecast based on historical data for the plurality of items and the plurality of retail locations.
13. The method of claim 9 , wherein the inventory information is retrieved on a scheduled basis, and wherein forecasting the demand comprises predicting current inventory for each of the multiple items in each of the plurality of retail locations.
14. The method of claim 9 , forecasting the demand comprises balancing inventory across the multiple retail locations to meet expected demand at the multiple retail locations after fulfillment of the suborders.
15. The method of claim 9 , wherein the customer order comprises an address and a deadline for delivery, and wherein the partitioning and assigning are further based on at least one of delivery time or delivery cost.
16. The method of claim 9 , wherein the inventory information is retrieved as part of retrieving operational data, the operational data further comprising at least one of daily sales reports, staffing records, shipping records, shipping rate cards, return policies, business hours, or pick decline estimation.
17. A non-transitory computer-readable storage medium storing instructions for fulfilling orders from a fulfillment network comprising a plurality of consumer-facing retail locations, the instructions, when executed by processing circuitry, causing the processing circuitry to perform operations comprising:
retrieving inventory information for the plurality of retail locations in the fulfillment network;
receiving a customer order for multiple items;
forecasting demand for each of the multiple items in each of the multiple retail locations;
based at least in part on the inventory information and the forecast demand, partitioning the customer order into multiple suborders and assigning the multiple suborders to multiple respective retail locations of the plurality of retail locations for fulfillment, each suborder comprising at least one of the multiple items; and
transmitting each suborder to the selected retail location for fulfillment.
18. The computer-readable storage medium of claim 17 , wherein assigning the multiple suborders to the respective retail locations comprises solving a linear programming problem.
19. The computer-readable storage medium of claim 17 , wherein the demand is forecast based on historical data for the plurality of items and the plurality of retail locations.
20. The computer-readable storage medium of claim 17 , wherein the inventory information is retrieved on a scheduled basis, and wherein forecasting the demand comprises predicting current inventory for each of the multiple items in each of the plurality of retail locations.