System and method for evaluating maintenance costs of products

• US 7,742,938 B2
• Filed: 08/28/2002
• Issued: 06/22/2010
• Est. Priority Date: 08/30/2001
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Blanchard, Jean Louis, Messatfa, Hammou, Lorin, Stephane, Pavillon, Christelle
• Primary Examiner(s): Karmis; Stefanos
• Application Number:
  US10/229,542
• Publication Number:
  US 20030055766A1
• Time in Patent Office: 2,855 Days
• Field of Search: 705/705, 705/7, 705/28, 705/29, 705/1, 705/35, 705/400
• US Class Current: 705/7.25
• CPC Class Codes: G06Q 10/06315 Needs-based resource requirements planning or analysis
• CPC Class Codes: G06Q 10/087 Inventory or stock management, e.g. order filling, procurement or balancing against orders
• CPC Class Codes: G06Q 10/0875 Itemisation or classification of parts, supplies or services, e.g. bill of materials
• CPC Class Codes: G06Q 20/201 Price look-up processing, e.g. updating
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0283 Price estimation or determination
• CPC Class Codes: G06Q 40/00 Finance; Insurance; Tax strategies; Processing of corporate or income taxes
• CPC Class Codes: G06Q 40/06 Asset management; Financial planning or analysis

Abstract

A method and system to evaluate the maintenance costs of products, having learning and application phases. Each phase is divided into two steps. The first analyzes product characteristics. The second is based on maintenance agreement conditions. During the first step of the learning phase, a first maintenance cost is estimated over the domain of a first variable representing product characteristics. Correction coefficients, based on other product characteristics, may be estimated to improve the first maintenance cost estimation. During the second step new correction coefficients are estimated according to maintenance agreement conditions. During the application phase, a first maintenance cost estimation is done according to the modality of the first variable, and adjusted depending on other product characteristics and maintenance agreement conditions.

Claims

1. A method for use in a data processing system to learn behavior of maintenance costs of products and determine maintenance costs of products, using a learning database containing product characteristics, maintenance agreement conditions and actual historical maintenance costs associated therewith, comprising the steps of:

receiving by the data processing system a selection of at least one product characteristic stored in said learning database;

determining by the data processing system, from said actual historical maintenance costs in the learning database, first maintenance cost estimations C₀(i) associated with each modality i of said at least one product characteristic and building a first table storing the modalities and said first maintenance cost estimations associated therewith according to the equation

2. The method of claim 1 wherein said step of determining first maintenance cost estimations comprises the step of normalizing said first maintenance cost estimations according to the at least one maintenance agreement condition.

3. The method of claim 1, further comprising the steps of:

selecting at least one other product characteristic from said learning database; and

,

determining, from said learning database, other maintenance cost correction coefficients associated with modalities of said at least one other product characteristic and building at least one other table storing the modalities of said at least one other product characteristic and said other maintenance cost correction coefficients associated therewith.

4. The method of claim 1, wherein said specified values of said second table are determined so that records of said learning database are uniformly distributed in said second table.

5. The method of claim 1, wherein the steps of determining maintenance cost correction coefficients and building a second table further comprise the steps of:

setting a window value for each of said at least one maintenance agreement condition;

for each of said specified values of said at least one maintenance agreement condition;

storing said specified value in said second table;

selecting records of said learning database whose values corresponding to said at least one maintenance agreement condition belong to a range defined by said specified value and said window value;

extrapolating a maintenance cost correction coefficient from the maintenance cost correction coefficients associated with said selected records; and

storing said extrapolated maintenance cost correction coefficient in said second table in association with said specified value.

6. The method of claim 5 wherein said extrapolated maintenance cost correction coefficient is a median value of the maintenance cost correction coefficients associated with said selected records.

7. The method of claim 1, further comprising a step of analyzing said learning database to detect aberrant records and isolating said aberrant records from said learning database.

8. The method of claim 1, further comprising the steps of:

inputting a value of a product corresponding to said at least one product characteristic;

determining a first maintenance cost estimation from said first table;

inputting a value, associated with the product, corresponding to said at least one maintenance agreement condition; and

determining the maintenance cost correction coefficient from said second table.

9. The method of claim 8, wherein said step of determining a maintenance cost correction coefficient from said second table, comprises the steps of:

selecting specified values of said second table bordering said product value corresponding to said at least one maintenance agreement condition; and

,

extrapolating said maintenance cost correction coefficient from the maintenance cost correction coefficients associated with said selected specified values.

10. The method of claim 9 wherein said extrapolation is a linear extrapolation.

11. The method of claim 8 wherein said step of determining a maintenance cost correction coefficient from said second table, comprises the steps of:

comparing said product value corresponding to said at least one maintenance agreement condition with said specified values of said second table; and

when said product value corresponding to said at least one maintenance agreement condition is bordered by specified values of the second table, determining said maintenance cost correction coefficient by performing a linear extrapolation on the maintenance cost correction coefficients associated with specified values of said second table bordering said product value.

12. The method of claim 8 further comprising the steps of:

inputting a product value corresponding to said at least one other product characteristic; and

,

determining at least one other maintenance cost correction coefficient from said at least one other table;

wherein the maintenance cost estimation is equal to said first maintenance cost estimation multiplied by said maintenance cost correction coefficient and said at least one other maintenance cost correction coefficient.

13. The method of claim 1, wherein said at least one maintenance agreement condition comprises lease duration.

14. The method of claim 1, wherein said products are vehicles.

15. A computerized data processing system for determining maintenance costs of products, comprising:

the data processing system having a storage system that stores a learning database comprising product characteristics, maintenance agreement conditions and associated historical maintenance costs;

the data processing system having an input system enabling selecting of at least one product characteristic and at least one maintenance agreement condition from the learning database;

the data processing system having a processor programmed to determine, from the learning database, first maintenance cost estimations C₀(i) associated with modalities i of the at least one product characteristic according to the equation

16. A program storage device readable by a data processing system, tangibly embodying a program of instructions executable by the data processing system to determine maintenance costs of products from a learning database comprising product characteristics, maintenance agreement conditions and associated historical maintenance costs, comprising:

a product characteristic code section that receives a selection of at least one product characteristic stored in the learning database;

a first table code section that determines, from the historical maintenance costs of the learning database, first maintenance cost estimations C₀(i) associated with modalities i of the at least one product characteristic according to the equation