Display space optimization

• US 10,417,606 B2
• Filed: 05/12/2015
• Issued: 09/17/2019
• Est. Priority Date: 05/12/2015
• Status: Active Grant

• Current Assignee: Oracle International Corporation (Oracle Corporation)
• Original Assignee: Oracle International Corporation (Oracle Corporation)
• Inventors: Panchamgam, Kiran V.
• Primary Examiner(s): Champagne, Luna
• Application Number:
  US14/709,702
• Publication Number:
  US 20160335586A1
• Time in Patent Office: 1,589 Days
• Field of Search: 705 28, 705 731, 705 22
• CPC Class Codes: G06Q 10/087 Inventory or stock management, e.g. order filling, procurement or balancing against orders

Abstract

Systems, methods, and other embodiments associated with assortment and display space optimization are described. In one embodiment, a method creates an optimal planogram. The example method includes receiving data describing i) a set of items described by item dimensions, ii) display space dimensions; iii) business rules, and iv) a key performance indicator. A set of possible shelf positions is identified for each item. An expected sales volume is calculated for each item and shelf position pair based, at least in part, on a selected demand model. The method includes providing i) the expected sales volume for the item and shelf position pairs, ii) a set of constraints that embody the business rules, and iii) an objective function to an optimization problem solver that computes a solution. Based on the solution, a planogram is output that specifies the assortment of items and respective optimal shelf positions of the items.

Claims

1. A non-transitory computer storage medium storing computer-executable instructions that when executed by a computer cause the computer to construct a planogram by:

receiving, by at least one processor, data describing i) a set of items selected from a corpus of items, where each item is described by item dimensions, ii) a display space;

iii) business rules that constrain the selection and positioning of items in the display space, and iv) a key performance indicator;

identifying, by at least the processor, a set of available shelf positions in the display space for each item in the set based, at least in part, on the item dimensions;

calculating for each item and available shelf position pair, by at least the processor, i) an expected sales volume and ii) an expected service level based, at least in part, on a selected demand model,

wherein the expected service level corresponds to a probability that the item will be in stock in the display space,

wherein each item and available shelf position pair corresponds to a combination of an item and an available shelf position;

providing, by at least the processor, a set of inputs to an optimization problem solver including i) the expected sales volume for the item and available shelf position pairs, ii) a set of constraints that embodies the business rules, iii) an objective function that expresses the key performance indicator as a function of the expected sales volumes and iv) the expected service level for the item and available shelf position pairs,

wherein the optimization problem solver;

processes the set of inputs to determine one or more solutions with the expected service level where a solution specifies i) an assortment of the items selected from the set of items and ii) for each item in the assortment, an optimal shelf position;

in response to failing to compute the one or more solutions with the expected service level, the optimization problem solver;

(i) drops the expected service level; and

(ii) computes, based upon the key performance indicator and without using the expected service level, another solution that specifies i) the assortment of the items selected from the set of items and ii) for each item in the assortment, the optimal shelf position; and

generating, by at least the processor, a planogram that specifies the assortment of items and respective optimal shelf positions of the items, wherein the planogram is representative of a physical arrangement of the items on physical shelves in a store.

2. The non-transitory computer storage medium of claim 1, where the selected demand model predicts the expected sales volume for each item and shelf position pair based on i) a quantity of item facings produced by positioning the item in the shelf position and ii) a demand transference from items in the corpus that are not included in the set of items.

3. The non-transitory computer storage medium of claim 1, where the objective function includes a first component that characterizes demand transference from items in the set of items not selected for the assortment to items selected for the assortment and a second component that characterizes a shelf contribution to demand for items in the set.

4. The non-transitory computer storage medium of claim 1, where the instructions further cause the computer to construct the planogram by:

determining that the display space comprises a pegboard having pegholes evenly arranged according to a horizontal peg spacing and a vertical peg spacing;

calculating the item dimensions for each item by, for each item;

rounding an actual item width up to a next integer value of horizontal peg spacing;

rounding an actual item height up to a next integer value of vertical peg spacing; and

determining shelf positions that correspond to blocks of pegholes by dividing the pegboard into a plurality of virtual shelves having respective dimensions determined based on a relationship between average item dimensions and dimensions of the pegboard; and

where the instructions for calculating an expected sales volume for each item and available shelf position pair based on a selected demand model include instructions for calculating an expected sales volume for each item and virtual shelf pair.

5. The non-transitory computer storage medium of claim 1, where the instructions further cause the computer to construct the planogram by:

prior to identifying a set of available shelf positions in the display space for each item in the set;

determining if the set of items violates any of the business rules; and

when the set of items violates a business rule, reporting infeasibility to a computing device without identifying a set of available shelf positions.

6. The non-transitory computer storage medium of claim 1, where the instructions further cause the computer to construct the planogram by:

reporting infeasibility to a computing device when the optimization problem solver fails to find the one or more solutions.

7. A computing system comprising:

at least one processor connected to at least one memory; and

a non-transitory computer readable medium with stored instructions that are configured as a set of logics executable by at least the processor, the logics comprising;

input logic configured to;

receive, by at least the processor, data describing i) a set of items selected from a corpus of items, where each item is described by item dimensions, ii) a display space;

iii) business rules as a set of constraints that constrain the selection and positioning of items in the display space, and iv) a key performance indicator;

identify, by at least the processor, a set of available shelf positions in the display space for each item in the set based, at least in part, on the item dimensions; and

calculate for each item and available shelf position pair, by at least the processor, i) an expected sales volume and ii) an expected service level based, at least in part, on a selected demand model;

wherein the expected service level corresponds to a probability that the item will be in stock in the display space,

wherein each item and available shelf position pair corresponds to a combination of an item and an available shelf position;

constraint logic configured to generate, by at least the processor, the set of constraints that embodies the business rules;

function logic configured to generate, by at least the processor, an objective function that expresses the key performance indicator as a function of the expected sales volumes; and

formulation logic configured to;

provide as a set of inputs, by at least the processor and to an optimization problem solver executed by at least the processor,

i) the expected sales volume for the item and available shelf position pairs,

ii) the set of constraints, iii) the objective function and iv) the expected service level for the item and available shelf position pairs;

wherein the optimization problem solver;

processes the set of inputs to determine one or more solutions with the expected service level where a solution specifies i) an assortment of the items selected from the set of items and ii) for each item in the assortment, an optimal shelf position;

in response to failing to compute the one or more solutions with the expected service level, the optimization problem solver;

(i) drops the expected service level; and

(ii) computes, based upon the key performance indicator and without using the expected service level, another solution that specifies i) the assortment of the items selected from the set of items and ii) for each item in the assortment, the optimal shelf position; and

wherein the formulation logic is further configured to;

generate, by at least the processor, a planogram that specifies the assortment of items and respective optimal shelf positions of the items, wherein the planogram is representative of a physical arrangement of the items on physical shelves in a store.

8. The computing system of claim 7, where the selected demand model predicts the expected sales volume for each item and shelf position pair based on i) a quantity of item facings produced by positioning the item in the shelf position and ii) a demand transference from items in the corpus that are not included in the set of items.

9. The computing system of claim 7, where the objective function includes a first component that characterizes demand transference from items in the set of items not selected for the assortment to items selected for the assortment and a second component that characterizes a shelf contribution to demand for items in the set.

10. The computing system of claim 7, where the business rules include a selected blocking strategy that defines whether related items are positioned in a horizontal blocks or vertical blocks within the display space.

11. The computing system of claim 7, where the input logic is further configured to determine that the display space comprises a pegboard having pegholes evenly arranged according to a horizontal peg spacing and a vertical peg spacing, the computing system further comprising:

dimension logic configured to calculate the item dimensions for each item by, for each item;

rounding an actual item width up to a next integer value of horizontal peg spacing; and

rounding an actual item height up to a next integer value of vertical peg spacing; and

shelf logic configured to determine shelf positions that correspond to blocks of pegholes by dividing the pegboard into a plurality of virtual shelves having respective dimensions determined based on a relationship between average item dimensions and dimensions of the pegboard; and

where the input logic is configured to calculate an expected sales volume for each item and shelf position pair based on a selected demand model

 

include instructions for calculating an expected sales volume for each item and virtual shelf pair.

12. The computing system of claim 7, where the input logic is further configured to:

report infeasibility to a computing device when the optimization problem solver fails to find a solution.

13. A computer-implemented method, comprising:

receiving, by at least one processor, data describing i) a set of items selected from a corpus of items, where each item is described by item dimensions, ii) display space dimensions;

iii) business rules that constrain the selection and positioning of items in the display space, and iv) a key performance indicator;

identifying, by at least the processor, a set of possible shelf positions in the display space for each item in the set based, at least in part, on the item dimensions;

calculating for each item and shelf position pair, by at least the processor, i) an expected sales volume and ii) an expected service level based, at least in part, on a selected demand model,

wherein the expected service level corresponds to a probability that at least one of the item will be available on a shelf,

wherein each item and available shelf position pair corresponds to a combination of an item and an available shelf position;

providing, by at least the processor, a set of inputs to an optimization problem solver including i) the expected sales volume for the item and shelf position pairs, ii) a set of constraints that embodies the business rules, iii) an objective function that expresses the key performance indicator as a function of the expected sales volumes and iv) the expected service level for the item and available shelf position pairs,

wherein the optimization problem solver;

processes the set of inputs to determine one or more solutions with the expected service level where a solution specifies i) an assortment of the items selected from the set of items and ii) for each item in the assortment, an optimal shelf position;

in response to failing to compute the one or more solutions with the expected service level, the optimization problem solver;

(i) drops the expected service level; and

i) computes, based upon the key performance indicator and without using the expected service level, another solution that specifies the assortment of the items selected from the set of items and ii) for each item in the assortment, the optimal shelf position; and

generating, by at least the processor, a planogram that specifies the assortment of items and respective optimal shelf positions of the items as computed by the optimization problem solver, wherein the planogram is representative of a physical arrangement of the items on physical shelves in a store.

14. The computer-implemented method of claim 13, where the selected demand model predicts the expected sales volume for each item and shelf position pair based on i) a quantity of item facings produced by positioning the item in the shelf position and ii) a demand transference from items in the corpus that are not included in the set of items.

15. The computer-implemented method of claim 13, where the objective function includes a first component that characterizes demand transference from items in the set of items not selected for the assortment to items selected for the assortment and a second component that characterizes a shelf contribution to demand for items in the set.

16. The computer-implemented method of claim 13, where the business rules include a selected blocking strategy that defines whether related items are positioned in a horizontal blocks or vertical blocks within the display space.

17. The computer-implemented method of claim 13, further comprising:

determining that the display space comprises a pegboard having pegholes evenly arranged according to a horizontal peg spacing and a vertical peg spacing;

calculating the item dimensions for each item by, for each item;

rounding an actual item width up to a next integer value of horizontal peg spacing; and

rounding an actual item height up to a next integer value of vertical peg spacing; and

determining shelf positions that correspond to blocks of pegholes by dividing the pegboard into a plurality of virtual shelves having respective dimensions determined based on a relationship between average item dimensions and dimensions of the pegboard; and

where calculating an expected sales volume for each item and shelf position pair based on a selected demand model comprises calculating an expected sales volume for each item and virtual shelf pair.

18. The computer-implemented method of claim 13, further comprising, prior to identifying a set of possible shelf positions in the display space for each item in the set:

determining if the set of items violates any of the business rules; and

when the set of items violates a business rule, reporting infeasibility to a computing device without identifying a set of possible shelf positions.

19. The computer-implemented method of claim 13, further comprising:

reporting infeasibility to a computing device when the optimization problem solver fails to find the one or more solutions.