Method for planning key component purchases to optimize revenue

• US 6,826,538 B1
• Filed: 07/28/1999
• Issued: 11/30/2004
• Est. Priority Date: 07/28/1999
• Status: Expired due to Term

• Current Assignee: JDA Software Group Incorporated (Panasonic Holdings Corporation)
• Original Assignee: i2 Technologies US Incorporated (Panasonic Holdings Corporation)
• Inventors: Singh, Vikas, Kalyan, Vibhu K., Starr, Jeffrey H.
• Primary Examiner(s): Weiss, John G.
• Assistant Examiner(s): OUELLETTE, JONATHAN P
• Application Number:
  US09/362,776
• Time in Patent Office: 1,952 Days
• Field of Search: 700/90, 700/99, 700/106, 705/7, 705/8, 705/400
• US Class Current: 705/7.25
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: G06Q 10/06315 Needs-based resource requirements planning or analysis
• CPC Class Codes: G06Q 30/0283 Price estimation or determination

Abstract

A method of calculating supplies of key components based on enhancing revenues in a made to order scheme. Products are designed by identifying product components, and combining the components in various combinations. Key component supplies are calculated using an algorithm that considers demand probability of component and product as well as calculating the marginal value of each component.

Claims

1. A computer implemented method for calculating a supply of a plurality of components for one or more products, comprising:

repeating the following until a set of new marginal values converges;

initializing a current marginal value for each component of the plurality of components;

repeating the following for each component of the plurality of components;

computing an average component price for a component according to the current marginal values;

for each product associated with the component, converting a product demand for the product into a component demand for the component;

computing a plurality of correlation coefficients according to the product demands and the component demands;

obtaining an expected mean and an expected standard deviation of the component demand according to the correlation coefficients;

obtaining a plurality of parameter values corresponding to the expected mean and the expected standard deviation of the component demand; and

computing a new marginal value for the component according to the average component price and the parameter values; and

calculating the supply of the components for the products according to the set of new marginal values.

2. The method of claim 1, wherein calculating the supply of the components for the products according to the set of new marginal values comprises dividing a cost of a component by an average component cost of the component, the cost of the component determined according to the new marginal value of the component.

3. The method of claim 1, further comprising utilizing a product control policy comprising a first come first served policy.

4. The method of claim 1, wherein the product demand is distributed according to a truncated normal distribution.

5. The method of claim 1, further comprising determining a final ordered quantity for a number of time periods by:

calculating an optimal supply and a revenue for each time period, from a last time period to a first time period, in accordance with the set of new marginal values;

repeating the following from the first time period to the last time period;

computing an expected leftover for a current time period; and

setting an ordered quantity of a next time period equal to the optimal supply of the next time period minus the expected leftover for the current time period; and

determining the final ordered quantity in accordance with the ordered quantity of the last time period.

6. The method of claim 5, further comprising determining a cost of inventory by computing a cost of carrying excess components from a current time period to a next time period.

7. The method of claim 5, wherein the time periods have different durations.

8. A computer implemented method for determining a plurality of supplies for a plurality of components to order, comprising:

determining the components for one or more products;

selecting a marginal value of each component comprising a non-zero value;

iteratively calculating the marginal values of the components until the marginal values converge; and

computing the supplies to order in accordance with the marginal values.

9. The method of claim 8, further comprising computing the supplies to order by dividing a cost of a component by an average component cost of the component, the cost of the component determined according to the new marginal value of the component.

10. The method of claim 8, further comprising utilizing a product control policy comprising a first come first served policy.

11. The method of claim 8, wherein the product demand is distributed according to a truncated normal distribution.

12. The method of claim 8, wherein iteratively calculating the marginal values comprises:

repeating the following, for each component, until a set of new marginal values converges;

computing an average component price for a component according to a plurality of current marginal values;

for each product associated with the component, converting a product demand for the product into a component demand for the component;

computing a plurality of correlation coefficients according to the product demands and the component demands;

obtaining an expected mean and an expected standard deviation of the component demand according to the correlation coefficients;

obtaining a plurality of parameter values corresponding to the expected mean and the expected standard deviation of the component demand; and

computing a new marginal value for the component according to the average component price and the parameter values.

13. The method of claim 8, wherein the products are manufactured under a make to order situation.

14. The method of claim 8, further comprising:

calculating an optimal supply and a revenue for each time period of a sequence of time periods, from a last time period to a first time period; and

repeating the following from the first time period to the last time period;

computing an expected leftover for a current time period; and

setting an ordered quantity of a next time period equal to the optimal supply of the next time period minus the expected leftover for the current time period.

15. The method of claim 14, further comprising determining a cost of inventory by calculating a cost of carrying excess components from a current time period to a next time period.

16. The method of claim 14, wherein the time periods have different durations.

17. A method for determining a plurality of marginal values for a plurality of components associated with one or more products, comprising:

determining the components associated with the products;

initializing a plurality of marginal values, each marginal value associated with a component; and

repeating the following for each component of the plurality of components until the marginal values converge;

calculating a price for a component according to a current marginal value;

obtaining component demand information associated with the component; and

computing a next marginal value in accordance with the price for the component and the component demand information associated with the component.

18. The method of claim 17, wherein obtaining component demand information associated with the component comprises:

for each product associated with the component, converting a product demand for the product into a component demand for the component;

computing a plurality of correlation coefficients according to the product demands and the component demands;

obtaining an expected mean and an expected standard deviation of the component demand according to the correlation coefficients; and

obtaining a plurality of parameter values corresponding to the expected mean and the expected standard deviation of the component demand in order to obtain component demand information associated with the component.

19. The method of claim 17, further comprising:

calculating an optimal supply for each time period of a sequence of time periods, from a last time period to a first time period in accordance with the converged marginal values; and

repeating the following from the first time period to the last time period;

computing an expected leftover for a current time period; and

setting an ordered quantity of a next time period equal to the optimal supply of the next time period minus the expected leftover for the current time period.

20. The method of claim 17, further comprising computing a supply associated with a component by:

calculating a cost of the component according to the marginal value associated with the component; and

computing a supply associated with the component according to the cost of the component and an average component cost of the component.

21. A system for determining a plurality of marginal values for a plurality of components associated with one or more products, comprising:

a database operable to store data associated with the components and the products;

one or more processors coupled to the database and collectively operable to;

determine the components associated with the products;

initialize a plurality of marginal values, each marginal value associated with a component; and

repeat the following for each component of the plurality of components until the marginal values converge;

calculating a price for a component according to a current marginal value;

obtaining component demand information associated with the component; and

computing a next marginal value in accordance with the price for the component and the component demand information associated with the component.

22. The system of claim 21, wherein the one or more processors are operable to obtain component demand information associated with the component by:

for each product associated with the component, converting a product demand for the product into a component demand for the component;

computing a plurality of correlation coefficients according to the product demands and the component demands;

obtaining an expected mean and an expected standard deviation of the component demand according to the correlation coefficients; and

obtaining a plurality of parameter values corresponding to the expected mean and the expected standard deviation of the component demand in order to obtain component demand information associated with the component.

23. The system of claim 21, wherein the one or more processors are operable to:

calculate an optimal supply for each time period of a sequence of time periods, from a last time period to a first time period in accordance with the converged marginal values; and

repeat the following from the first time period to the last time period;

computing an expected leftover for a current time period; and

setting an ordered quantity of a next time period equal to the optimal supply of the next time period minus the expected leftover for the current time period.

24. The system of claim 21, wherein the one or more processors are operable to compute a supply associated with a component by:

calculating a cost of the component according to the marginal value associated with the component; and

computing a supply associated with the component according to the cost of the component and an average component cost of the component.

25. Software for determining a plurality of marginal values for a plurality of components associated with one or more products, the software embodied in media and when executed operable to:

determine the components associated with the products;

initialize a plurality of marginal values, each marginal value associated with a component; and

repeat the following for each component of the plurality of components until the marginal values converge;

calculating a price for a component according to a current marginal value;

obtaining component demand information associated with the component; and

computing a next marginal value in accordance with the price for the component and the component demand information associated with the component.

26. The software of claim 25, operable to obtain component demand information associated with the component by:

for each product associated with the component, converting a product demand for the product into a component demand for the component;

computing a plurality of correlation coefficients according to the product demands and the component demands;

obtaining an expected mean and an expected standard deviation of the component demand according to the correlation coefficients; and

obtaining a plurality of parameter values corresponding to the expected mean and the expected standard deviation of the component demand in order to obtain component demand information associated with the component.

27. The software of claim 25, operable to:

calculate an optimal supply for each time period of a sequence of time periods, from a last time period to a first time period in accordance with the converged marginal values; and

repeat the following from the first time period to the last time period;

computing an expected leftover for a current time period; and

setting an ordered quantity of a next time period equal to the optimal supply of the next time period minus the expected leftover for the current time period.

28. The software of claim 25, operable to compute a supply associated with a component by:

calculating a cost of the component according to the marginal value associated with the component; and

computing a supply associated with the component according to the cost of the component and an average component cost of the component.

29. A system for determining a plurality of marginal values for a plurality of components associated with one or more products, comprising:

means for determining the components associated with the products;

means for initializing a plurality of marginal values, each marginal value associated with a component; and

means for repeating the following for each component of the plurality of components until the marginal values converge;

calculating a price for a component according to a current marginal value;

obtaining component demand information associated with the component; and

computing a next marginal value in accordance with the price for the component and the component demand information associated with the component.

30. A method for determining a plurality of marginal values for a plurality of components associated with one or more products, comprising:

determining the components associated with the products;

initializing a plurality of marginal values, each marginal value associated with a component; and

repeating the following for each component of the plurality of components until the marginal values converge;

calculating a price for a component according to a current marginal value;

obtaining component demand information associated with the component, for each product associated with the component, converting a product demand for the product into a component demand for the component, computing a plurality of correlation coefficients according to the product demands and the component demands, obtaining an expected mean and an expected standard deviation of the component demand according to the correlation coefficients, and obtaining a plurality of parameter values corresponding to the expected mean and the expected standard deviation of the component demand in order to obtain component demand information associated with the component; and

computing a next marginal value in accordance with the price for the component;

calculating an optimal supply for each time period of a sequence of time periods, from a last time period to a first time period in accordance with the converged marginal values; and

repeating the following from the first time period to the last time period;

computing an expected leftover for a current time period, and setting an ordered quantity of a next time period equal to the optimal supply of the next time period minus the expected leftover for the current time period; and

computing a supply associated with a component by calculating a cost of the component according to the marginal value associated with the component, and computing a supply associated with the component according to the cost of the component and an average component cost of the component.