System and method for managing a collection of stock replenishment systems

• US 20080147477A1
• Filed: 12/15/2006
• Published: 06/19/2008
• Est. Priority Date: 12/15/2006
• Status: Active Grant

• Current Assignee: Callahan Cellular LLC (Intellectual Ventures LLC)
• Original Assignee: Ziti Technologies LLC (Intellectual Ventures LLC)
• Inventors: McCormick, Kevin Lee
• Granted Patent: US 7,896,244 B2
• Time in Patent Office: Days
• US Class Current: 705/10
• CPC Class Codes: G06Q 10/087 Inventory or stock management, e.g. order filling, procurement or balancing against orders
• CPC Class Codes: G06Q 20/203 Inventory monitoring

Abstract

The present invention provides a method of managing a stock replenishment system in a way that explicitly controls the in-stock rate. Also provided by the present invention is a method of managing a collection of stock replenishment systems in a way that the combined in-stock rate of the collection is controlled to a selected value. In addition, the present invention provides a method to set up a collection of stock replenishment systems in replenishment software systems in an identical fashion while controlling the combined in-stock rate. The methods of the present invention use point-of-sale data to determine packages-per-shopper rates, which are used as one of the inputs to statistical models of multiple-day retail sales.

Claims

1. A method for managing a stock replenishment system, said system comprising:

a. selecting an out-of-stock probability for a given item for any given day;

b. obtaining point-of-sale data for the given item over a period of time;

c. determining from the point-of-sale data the statistical distribution of the given item'"'"'s packages per shopper;

d. estimating or determining an expected daily sales for the given item;

e. determining a multi-day maximal sales for the given item from the expected daily sales of the given item and the given item'"'"'s packages per shopper distribution which corresponds to the out-of-stock probability; and

f. setting a reorder point in the stock replenishment software program based on the maximal sales.

2. The method according to claim 1, wherein the out-of-stock probability is selected to be between 0.01% and 10%.

3. The method according to claim 2, wherein the out-of stock probability is selected to be between 0.1% and 1.0%.

4. The method according to claim 1, wherein the point-of-sale data is collected over a period of 7 days to 180 days.

5. The method according to claim 4, wherein the point-of-sale data is collected over a period of 60 days to 120 days.

6. The method according to claim 1, wherein the expected daily sales is determined from the point-of-sale data.

7. The method according to claim 6, wherein the expected daily sales is determined from a trailing average daily sales.

8. The method according to claim 1, wherein the expected daily sales is estimated from a near-term sales forecast.

9. The method according to claim 1, wherein the multi-day maximal sales are determined by calculating a parameter of a Compound Poisson distribution from point-of-sale data and using the parameter to determine the maximal sales which corresponds to the out-of-stock probability.

10. The method according to claim 9, wherein an average-shopper-per-day parameter of the Compound Poisson distribution is determined by dividing the expected daily sales by the average packages per shopper.

11. The method according to claim 10, wherein the average-shoppers-per-day parameter of the Compound Poisson distribution is multiplied by the given item'"'"'s lead-time plus one-day.

12. The method according to claim 9, wherein a Negative Binomial distribution is used as an approximation of the Compound Poisson distribution.

13. The method according to claim 12, wherein an average-shoppers-per-day parameter of the Negative Binomial distribution is determined by dividing the expected daily sales by the average packages per shopper.

14. The method according to claim 13, wherein the average-shoppers-per-day parameter of the Negative Binomial distribution is multiplied by the given item'"'"'s lead-time plus one-day.

15. The method according to claim 12, wherein an average-shoppers-per-day parameter of the Negative Binomial distribution is determined from the statistical distribution of the given item'"'"'s packages per shopper.

16. A method of managing a collection of stock replenishment systems controlling one or more items at one or more stores, said method comprising:

a. defining a combined in-stock objective for all items in all stores controlled by the collection of stock replenishment systems as a desired fraction of the stock replenishment systems that are in-stock on any given day;

b. defining a meets objective for the percentage of time that the combined in-stock objective is desired to be met across all stores and all items controlled by the collection of stock replenishment systems;

c. determining a common single-store single-item out-of-stock probability employed by each of the collection of stock replenishment systems from the defined combined in-stock objective and the defined meets objective;

d. obtaining point-of-sale data for each store and each item controlled by the collection of stock replenishment systems;

e. determining a multi-day maximal sales for each store and each item on each stock replenishment system on the collection of stock replenishment systems which corresponds to the common single-store single-item out-of-stock probability; and

f. setting the reorder point for each stock replenishment system software program based on the maximal sales.

17. The method according to claim 16, further comprising determining from the point-of-sale data a given item'"'"'s average packages per shopper and determining or estimating the expected daily sales for a given item and using expected daily sales and packages per shopper to determine the multi-day maximal sales for each item.

18. The method according to claim 17, wherein the maximal sales are determined by calculating parameters of a Compound Poisson distribution from point-of-sale data and using the parameters to determine the maximal sales.

19. The method according to claim 18, wherein the parameters of the Compound Poisson distribution are determined by calculating the expected number of shoppers per day, the average number of packages per shopper and the standard deviation of the average number of packages per shopper.

20. The method according to claim 19, wherein the parameters of the Compound Poisson distribution are further calculated by multiplying the expected number of shoppers per day by a lead-time plus one day.

21. The method according to claim 16, wherein determining the maximal sales comprises an iterative method to find the smallest integer value of the maximal sales which corresponds to the single store out-of-stock probability.

22. The method according to claim 16, wherein the maximal sales are determined by calculating a parameter of a Compound Poisson distribution from the point-of-sale data and using the parameter to determine the maximal sales which correspond to the single store out-of-stock probability.

23. The method according to claim 22, wherein the parameters of the Compound Poisson distribution are an expected number of shoppers per day time a lead time plus one day.

24. The method according to claim 23, wherein the expected number of shoppers per day is determined by dividing the expected daily sales by the average packages per shopper, wherein the expected daily sales is determined by a one-time analysis of the point-of-sale data, trailing average daily sales analysis, or a near-term sales forecast, and the average packages per shopper is determined from a one-time analysis of the point-of-sale data.

25. The method according to claim 16, wherein the in-stock objective is selected to be between 90% and 99.99% of the time.

26. The method according to claim 25, wherein the in-stock objective is selected to be between 99% and 99.9% of the time.

27. The method according to claim 16, wherein the point-of-sale data is collected over a period of 7 days to 180 days.

28. The method according to claim 27, wherein the point-of-sale data is collected over a period of 60 days to 120 days.

29. The method according to claim 16, wherein the meets objective is between 80% and 99.9% of the time.

30. The method according to claim 29, wherein the meets objective is between 85% and 95% of the time.

31. The method according to claim 16, wherein the in-stock objective is selected to be between 90% and 99.99% of the time, the point-of-sale data is collected over a period of 7 days to 180 days, and the meets objective is between 80% and 99.9% of the time.

32. The method according to claim 31, wherein the in-stock objective is selected to be between 99% and 99.9%, of the time, the point-of-sale data is collected over a period of 60 days to 120 days, and the meets objective is between 85% and 95% of the time.

33. The method according to claim 18, wherein a Negative Binomial distribution is used as an approximation of the Compound Poisson distribution.

34. The method according to claim 20, wherein a Negative Binomial distribution is used as an approximation of the Compound Poisson distribution.

35. The method according to claim 22, wherein a Negative Binomial distribution is used as an approximation of the Compound Poisson distribution.

36. A method of managing a collection of stock replenishment systems across two or more products at one or more stores having the same lead-time, said method comprising:

a. determine which stores and which items at those stores have the same lead-time;

b. defining a combined in-stock objective for all items in all stores controlled by the collection of stock replenishment systems as a desired fraction of the stock replenishment systems that are in-stock on any given day;

c. defining a meets objective for the percentage of time that the combined in-stock objective is desired to be met across all stores and all items controlled by the collection of stock replenishment systems;

d. determining a single-store out-of-stock probability across the collection of stock replenishment systems from the defined combined in-stock objective and the defined meets objective;

e. determining a range of average package per shopper that are similar and select the highest average packages per shopper;

f. estimating parameters of a Negative Binomial distribution for the item with the highest average packages per shopper;

g. approximating the reorder point as a linear function based on the parameters of the Negative Binomial distribution, wherein the linear function is a slope times expected daily sales plus a safety stock, wherein the safety stock is set as an intercept of the linear function with the axis where the expected daily sales is equal to zero; and

h. setting the collection of stock replenishment software programs which have the same lead-time to calculate the reorder point as a slope times the expected daily sales plus the intercept point.

40. The method according to claim 36, wherein the expected daily sales is less than about 20 items per day.

41. The method according to claim 36, wherein the parameters of the Negative Binomial distribution are determined by calculating the average number of shoppers per day, the average number of packages per shopper and the standard deviation of the average number of packages per shopper.

42. The method according to claim 41, wherein the parameters of the Negative Binomial distribution are further calculated by multiplying the expected number of shoppers per day by a lead-time plus one day.

43. The method according to claim 36, wherein the in-stock objective is selected to be between 90% and 99.99% of the time.

44. The method according to claim 43, wherein the in-stock objective is selected to be between 99% and 99.9% of the time.

45. The method according to claim 36, wherein the point-of-sale data is collected over a period of 7 days to 180 days.

46. The method according to claim 45, wherein the point-of-sale data is collected over a period of 60 days to 120 days.

47. The method according to claim 36, wherein the meets objective is between 80% and 99.9% of the time.

48. The method according to claim 47, wherein the meets objective is between 85% and 95% of the time.

49. The method according to claim 36, wherein the in-stock objective is selected to be between 90% and 99.99% of the time, the point-of-sale data is collected over a period of 7 days to 180 days, and the meets objective is between 80% and 99.9% of the time.

50. The method according to claim 49, wherein the in-stock objective is selected to be between 99% and 99.9%, of the time, the point-of-sale data is collected over a period of 60 days to 120 days, and the meets objective is between 85% and 95% of the time.

37. The method according to claim 37, wherein the expected daily sales are calculated from a trailing average daily sales analysis, or a near-term sales forecast,

38. The method according to claim 37, wherein the similar average packages per shopper are within 40% of one another.

39. The method according to claims 38, wherein similar average packages per shopper are within 30% of one another.