System and method of reinforced machine-learning retail allocation

1. A system of allocation planning, comprising:

a network, automated warehousing equipment and a server, comprising a processor and memory, the server operably connected over the network to the automated warehousing equipment, the server further configured to:

calculate, using a reward-penalty function as part of a reinforcement learning process, a reward for a historical allocation of a product to one or more stores associated with a retailer, wherein the reward-penalty function comprises product margin, inventory carrying cost and opportunity cost represented by Bellman's equation;

simulate what-if scenarios for the historical allocation to identify an allocation having a greater reward than the historical allocation;

allocate a quantity of a product for a current allocation to the one or more stores based, at least in part, on a distance calculation of one or more independent variables for the historical allocation and the current allocation and the identified allocation having the greater reward then the historical allocation; and

responsive to a difference between a current inventory level and a constrained allocation quantity, retrieve a quantity of the product equal to the difference between the current inventory level and the constrained allocation quantity for transportation to stores by sending instructions over the network to the automated warehousing equipment of one or more distribution centers to automatically retrieve the quantity of the product.

2. The system of claim 1 , wherein the server is further configured to:

calculate an unconstrained allocation quantity representing a product need at the one or more stores.

3. The system of claim 1 , wherein the server is further configured to:

calculate a constrained allocation quantity representing an optimal allocation quantity.

4. The system of claim 3 , wherein calculate a constrained allocation quantity representing an optimal allocation quantity comprises a minimum presentation quantity constraint for at least one of the one or more stores.

5. The system of claim 3 , wherein calculate a constrained allocation quantity representing an optimal allocation quantity comprises a supply level constraint at one or more distribution centers and a minimum presentation quantity constraint for at least one of the one or more stores.

6. The system of claim 5 , wherein the independent variables comprise one or more of:

sales average;

sales variability;

sent receipts;

lags of demand;

seasonal factors;

store clusters;

climate data; and

market trends.

7. A computer-implemented method of allocation planning, comprising:

networking a computer with automated warehousing equipment;

calculating, by the computer comprising a processor and memory, using a reward-penalty function as part of a reinforcement learning process, a reward for a historical allocation of a product to one or more stores associated with a retailer, wherein the reward-penalty function comprises product margin, inventory carrying cost and opportunity cost represented by Bellman's equation;

simulating, by the computer, what-if scenarios for the historical allocation to identify an allocation having a greater reward than the historical allocation;

allocating, by the computer, a quantity of a product for a current allocation to the one or more stores based, at least in part, on a distance calculation of one or more independent variables for the historical allocation and the current allocation and the identified allocation having the greater reward then the historical allocation; and

responsive to a difference between a current inventory level and a constrained allocation quantity, retrieve a quantity of the product equal to the difference between the current inventory level and the constrained allocation quantity for transportation to stores by sending instructions over the network to the automated warehousing equipment of one or more distribution centers to automatically retrieve the quantity of the product.

8. The computer-implemented method of claim 7 , further comprising:

calculating, by the computer, an unconstrained allocation quantity representing a product need at the one or more stores.

9. The computer-implemented method of claim 7 , further comprising:

calculating, by the computer, a constrained allocation quantity representing an optimal allocation quantity.

10. The computer-implemented method of claim 9 , wherein calculating a constrained allocation quantity representing an optimal allocation quantity comprises a minimum presentation quantity constraint for at least one of the one or more stores.

11. The computer-implemented method of claim 9 , wherein calculating a constrained allocation quantity representing an optimal allocation quantity comprises a supply level constraint at one or more distribution centers and a minimum presentation quantity constraint for at least one of the one or more stores.

12. The computer-implemented method of claim 11 , wherein the independent variables comprise one or more of:

sales average;

sales variability;

sent receipts;

lags of demand;

seasonal factors;

store clusters;

climate data; and

market trends.

13. A non-transitory computer-readable medium embodied with software, the software when executed:

networks a computer with automated warehousing equipment;

calculates, using a reward-penalty function as part of a reinforcement learning process, a reward for a historical allocation of a product to one or more stores associated with a retailer, wherein the reward-penalty function comprises product margin, inventory carrying cost and opportunity cost represented by Bellman's equation;

simulates what-if scenarios for the historical allocation to identify an allocation having a greater reward than the historical allocation;

allocates a quantity of a product for a current allocation to the one or more stores based, at least in part, on a distance calculation of one or more independent variables for the historical allocation and the current allocation and the identified allocation having the greater reward then the historical allocation; and

responsive to a difference between a current inventory level and a constrained allocation quantity, retrieves a quantity of the product equal to the difference between the current inventory level and the constrained allocation quantity for transportation to stores by sending instructions over the network to the automated warehousing equipment of one or more distribution centers to automatically retrieve the quantity of the product.

14. The non-transitory computer-readable medium of claim 13 , the software when executed further:

calculates an unconstrained allocation quantity representing a product need at the one or more stores.

15. The non-transitory computer-readable medium of claim 13 , the software when executed further:

calculates a constrained allocation quantity representing an optimal allocation quantity.

16. The non-transitory computer-readable medium of claim 15 , wherein calculates a constrained allocation quantity representing an optimal allocation quantity comprises a minimum presentation quantity constraint for at least one of the one or more stores.

17. The non-transitory computer-readable medium of claim 15 , wherein calculates a constrained allocation quantity representing an optimal allocation quantity comprises a supply level constraint at one or more distribution centers and a minimum presentation quantity constraint for at least one of the one or more stores.