Compensation data prediction

• US 7,805,354 B2
• Filed: 06/17/2002
• Issued: 09/28/2010
• Est. Priority Date: 06/15/2001
• Status: Expired due to Fees

• Current Assignee: SCMC Acquisition, LLC
• Original Assignee: Salary.com
• Inventors: Zhang, Yong, Plunkett, Gregory K., Fortier, Keith E., Linn, Andrew L., Coleman, William H.
• Primary Examiner(s): Jeanty; Romain
• Application Number:
  US10/502,837
• Publication Number:
  US 20050234759A1
• Time in Patent Office: 3,025 Days
• Field of Search: 705/7, 705/10
• US Class Current: 705/37
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: G06Q 10/063 Operations research, analysis or management
• CPC Class Codes: G06Q 10/06375 Prediction of business process outcome or impact based on a proposed change
• CPC Class Codes: G06Q 10/06398 Performance of employee with respect to a job function
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 10/105 Human resources
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: G06Q 30/0205 Location or geographical consideration
• CPC Class Codes: G06Q 30/0206 Price or cost determination based on market factors
• CPC Class Codes: G06Q 40/04 Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
• CPC Class Codes: G06Q 40/08 Insurance
• CPC Class Codes: G06Q 90/00 Systems or methods specially adapted for administrative, commercial, financial, managerial or supervisory purposes, not involving significant data processing
• CPC Class Codes: G16H 40/20 for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms

Abstract

A method of predicting compensation data includes obtaining compensation data, associated with a job category, with at least one datum being associated with each of a plurality of characteristics associated with the job category, determining values of factors, associated with respective ones of the characteristics, and a base value that when used as operands of a function yield estimates of the obtained data such that relationships between the estimates and corresponding obtained compensation data satisfy at least one criterion, and using a portion of the values of factors and the base value by a computer to automatically obtain estimates of compensation data.

Claims

1. A method, for use with a computer system having a processor, of predicting compensation data, the method comprising:

obtaining and storing, in the computer system having a processor, compensation data, associated with a job category, with at least one datum being associated with each of a plurality of characteristics associated with the job category;

determining values of factors, associated with respective ones of the characteristics, and a base value that, when used as operands of a function executed by the computer system having a processor, yield computer generated estimates of the obtained data such that relationships between the estimates and corresponding obtained compensation data satisfy at least one criterion;

using a portion of the values of factors and the base value, by the computer system having a processor, to automatically obtain estimates of compensation data;

deriving, using the computer system having a processor, reference data using the obtained compensation data and the values of factors;

aggregating, using the computer system having a processor, the reference data to determine the base value;

comparing, using the computer system having a processor, estimated compensation data with obtained compensation data of the same job and having the same associated characteristics as the estimated compensation data;

adjusting the values of the factors as appropriate depending upon results of comparing the estimated and obtained compensation data; and

repeating the deriving, aggregating, using, comparing, and adjusting until comparing the estimated and obtained compensation data satisfy the at least one criterion.

2. The method of claim 1 wherein using the portion of the values of factors and the base value includes using each combination of values of factors for which values are determined.

3. The method of claim 1 wherein the aggregating comprises averaging the reference data using the computer system having a processor.

4. The method of claim 1 wherein the characteristics are scope criteria associated with jobs.

5. The method of claim 4 wherein the characteristics include at least one of geographic region, size of organization, industry, and seniority.

6. The method of claim 1 further comprising comparing, using the computer system having a processor, indicia associated with obtained data and estimated data respectively.

7. The method of claim 6 wherein the indicia are of estimated and obtained data.

8. The method of claim 1 wherein the relationships are differences between estimated and obtained data associated with the same job and same characteristics.

9. The method of claim 8 wherein the at least one criterion is that the differences are within a magnitude limit.

10. The method of claim 1 wherein the relationships are ratios between estimated and obtained data associated with the same job and same characteristics.

11. The method of claim 10 wherein the at least one criterion is that the ratios are within a magnitude limit.

12. The method of claim 1 wherein the obtained data are associated with at least two job categories, and the method further comprises:

determining a job-to-job factor relating compensation data of a first job category to compensation of a second job category; and

applying the job-to-job factor to a selected datum of the first job category to determine a datum of the second job category.

13. The method of claim 12 wherein the selected and determined data are compensation data.

14. The method of claim 12 wherein the selected and determined data are values of factors.

15. The method of claim 1 further comprising combining, using the computer system having a processor, the estimates of compensation data and the obtained compensation data.

16. The method of claim 15 wherein the combining includes weighting at least one of the estimates of compensation data and the obtained compensation data.

17. The method of claim 1 further comprising transmitting indicia of the estimates of compensation data via a communications network to a destination for display at the destination.

18. A system for estimating compensation data, the system comprising:

a communications network interface configured to be coupled to a communications network;

a storage device configured to store compensation data; and

a processor coupled to the network interface and to the storage device and configured to;

calculate a base value associated with the stored compensation data by solving a relationship for reference data using the stored compensation data and predetermined values of training factors associated with scope criteria of the compensation data, the relationship relating the reference data, compensation data, and the values of the training factors, the processor further configured to calculate the base value by combining the reference data to determine the base value; and

determine estimated compensation data by solving the relationship for the compensation data using values of the training factors and the base value, and

wherein the processor is further configured to re-calculate the base value and re-determine estimated compensation data using different values of factors if relationships between the estimated compensation data and the stored compensation data fail to satisfy at least one predetermined criterion.

19. The system of claim 18 wherein the processor is further configured to compare the estimated compensation data and the stored compensation data and to provide indicia of the comparison.

20. The system of claim 18 wherein the relationships are differences and the at least one predetermined criterion is whether the differences are within a threshold value.

21. The system of claim 18 wherein the relationships are ratios and the at least one predetermined criterion is whether the ratios are within a threshold value.

22. The system of claim 18 further comprising a user interface coupled to the processor and configured to provide values of the factors.

23. The system of claim 18 wherein the processor is further configured to combine the estimated and stored compensation data.

24. The system of claim 23 wherein the processor is further configured to provide the combined compensation data to the network interface.

25. The system of claim 24 wherein the processor is configured to receive indicia of weighting of the stored and estimated compensation data and to provide weighted combinations of the stored and estimated compensation data to the network interface for display on a display device coupled to the communications network.

26. A system for estimating compensation data, the system comprising:

a communications network interface configured to be coupled to a communications network;

a storage device configured to store compensation data; and

a processor coupled to the network interface and to the storage device and configured to;

calculate a base value associated with the stored compensation data by solving a relationship for reference data using the stored compensation data and predetermined values of training factors associated with scope criteria of the compensation data, the relationship relating the reference data, compensation data, and the values of the training factors, the processor further configured to calculate the base value by combining the reference data to determine the base value; and

determine estimated compensation data by solving the relationship for the compensation data using values of the training factors and the base value,

wherein the processor is further configured to determine initial values of the factors by combining compensation data points associated with a particular job to determine a neutral data point and comparing the neutral data point with a data points associated with the scope criteria.

27. A method, for use with a computer system having a processor, of predicting compensation data, the method comprising:

collecting, and storing in the computer system having a processor, compensation data for each of a plurality of jobs, at least one datum being associated with each of a respective plurality of associated scope criteria for each job;

deriving, using the computer system having a processor, reference data for each of the plurality of jobs in accordance with a function relating collected compensation data, the reference data, and respective training factors indicative of the respective associated scope criteria;

aggregating, using the computer system having a processor, the reference data associated with each of a plurality of jobs to determine respective aggregated reference data;

using a portion of the respective training factors and the respective aggregated reference data to determine, using the computer system having a processor, respective estimated compensation data for each of the plurality jobs;

comparing, using the computer system having a processor, the respective estimated compensation data with collected compensation data of the same job and having the same associated training factors;

iterating the respective training factors as appropriate;

repeating the deriving, aggregating, using, comparing, and iterating until the compared estimated and collected compensation data satisfy at least one comparison criterion;

determining at least one job-to-job training factor associating compensation data of a first job to compensation data of a second job, and

estimating, using the computer system having a processor, compensation data of the first job for a combination of training factors using estimated compensation data of the second job with the same combination of training factors.

28. The method of claim 27 wherein the using determines estimated compensation data for all combinations of associated training factors for each of the jobs.