Development of electronic employee selection systems and methods

• US 7,562,059 B2
• Filed: 08/11/2004
• Issued: 07/14/2009
• Est. Priority Date: 08/03/2000
• Status: Expired due to Fees

• Current Assignee: Cadient LLC
• Original Assignee: Kronos Talent Management Incorporated (Seahawk Acquisition Corp.)
• Inventors: Smith, David R., Smith, John R., Becker, Richard W., Clainos, Deme M., Scarborough, David J., Chambless, Bjorn, Check, Thomas F., Eng, Maxwell W., Mertz, Adam N., Paajanen, George E., Levy, Joel R.
• Primary Examiner(s): Vincent; David R
• Assistant Examiner(s): Wong; Lut
• Application Number:
  US10/917,252
• Publication Number:
  US 20050114279A1
• Time in Patent Office: 1,798 Days
• Field of Search: 706/21, 706/45, 706/46, 705/11
• US Class Current: 706/21
• CPC Class Codes: G06Q 10/063 Operations research, analysis or management
• CPC Class Codes: G06Q 10/063118 Staff planning in a project environment
• CPC Class Codes: G06Q 10/0639 Performance analysis of employees; Performance analysis of enterprise or organisation operations
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 10/1053 Employment or hiring
• CPC Class Codes: G06Q 30/08 Auctions
• CPC Class Codes: G09B 5/00 Electrically-operated educational appliances working with questions and answers G09B7/00; simulators G09B9/00; advertising or displaying in general G09F
• CPC Class Codes: G09B 7/00 Electrically-operated teaching apparatus or devices working with questions and answers mechanically operated G09B3/00; computing arrangements G06F
• CPC Class Codes: G09B 7/02 of the type wherein the student is expected to construct an answer to the question which is presented or wherein the machine gives an answer to the question presented by a student

Abstract

An automated employee selection system can use a variety of techniques to provide information for assisting in selection of employees. For example, pre-hire and post-hire information can be collected electronically and used to build an artificial-intelligence based model. The model can then be used to predict a desired job performance criterion (e.g., tenure, number of accidents, sales level, or the like) for new applicants. A wide variety of features can be supported, such as electronic reporting. Pre-hire information identified as ineffective can be removed from a collected pre-hire information. For example, ineffective questions can be identified and removed from a job application. New items can be added and their effectiveness tested. As a result, a system can exhibit adaptive learning and maintain or increase effectiveness even under changing conditions.

Claims

1. A method of constructing a model predicting employment performance based on a set of input employment parameters, the method comprising:

receiving a set of input parameters indicating pre-hire psychological assessment and bio-data characteristics of an employee, wherein the pre-hire psychological assessment and bio-data characteristics are available before hiring the employee and are collected electronically from the employee as pre-hire answers to questions, wherein the questions comprise psychological assessment questions and bio-data questions;

receiving a set of one or more output parameters indicating one or more post-hire outcomes observed after hiring the employee, wherein the one or more post-hire outcomes comprise one or more post-hire outcomes selected from the group consisting of number of accidents, sales level, units produced, attendance, number of disciplinary incidents, dollar sales per hour, promotions, salary increases, probationary survival, and completion of training programs;

identifying respective of the input parameters as ineffective predictors of the one or more post-hire outcomes, wherein the identifying comprises evaluating whether a plurality of sets of permutations of the input parameters are effective in predicting the one or more post-hire outcomes, and wherein at least one of the sets of permutations comprises at least one of the psychological assessment questions and at least one of the bio-data questions, and wherein the identifying comprises determining whether a random relationship between a respective permutation and the one or more post-hire outcomes is exhibited;

reducing the input parameters to a subset of input parameters for use as remaining input features to a neural network, wherein the reducing comprises removing the ineffective predictors, and wherein the remaining input features comprise a mix of answers to psychological assessment questions and answers to bio-data questions; and

training a neural network with the one or more observed post-hire outcomes and the remaining input features, comprising a mix of answers to psychological assessment questions and answers to bio-data questions, to predict the one or more post-hire outcomes for a job applicant for use in a hiring recommendation based at least on pre-hire answers by the job applicant to questions corresponding to the remaining input features, wherein the neural network is stored in a computer-readable medium.

2. The method of claim 1 further comprising:

performing performance-driven item rotation, wherein the performance-driven item rotation comprises dropping one or more of the input parameters and retraining a neural network.

3. The method of claim 1 further comprising:

monitoring quantity of incoming predictor case data and criterion case data with a sample size monitor, wherein the predictor case data comprises employee psychological assessment and bio-data characteristics for applicants, and the criterion case data comprises post-hire outcomes observed after hiring employees; and

with the sample size monitor, providing an indication when a threshold number of predictor-criterion paired cases have accumulated.

4. The method of claim 1 wherein the psychological assessment questions comprise a question asking whether the job applicant agrees with a statement.

5. The method of claim 1 wherein the bio-data questions comprise a question asking how long the job applicant plans to stay if hired.

6. The method of claim 1 wherein the neural network is configured to generate a single value when the pre-hire answers by the job applicant are applied.

7. The method of claim 1 wherein the neural network is configured to generate a range when the pre-hire answers by the job applicant are applied.

8. The method of claim 1 wherein the neural network is configured to generate a rank when the pre-hire answers by the job applicant are applied.

9. One or more computer-readable media having computer-executable instructions for performing a method of constructing a model predicting employment performance based on a set of input employment parameters, the method comprising:

receiving a set of input parameters indicating pre-hire psychological assessment and bio-data characteristics of an employee, wherein the pre-hire psychological assessment and bio-data characteristics are available before hiring the employee and are collected electronically from the employee as pre-hire answers to questions, wherein the questions comprise psychological assessment questions and bio-data questions;

receiving a set of one or more output parameters indicating one or more post-hire outcomes observed after hiring the employee, wherein the one or more post-hire outcomes comprise one or more post-hire outcomes selected from the group consisting of number of accidents, sales level, sales produced, units produced, attendance, number of disciplinary incidents, dollar sales per hour, promotions, salary increases, probationary survival, and completion of training programs;

identifying respective of the input parameters as ineffective predictors of the one or more post-hire outcomes, wherein the identifying comprises evaluating whether a plurality of sets of permutations of the input parameters are effective in predicting the one or more post-hire outcomes, and wherein at least one of the sets of permutations comprises at least one of the psychological assessment questions and at least one of the bio-data questions, and wherein the identifying comprises determining whether a random relationship between a respective permutation and the one or more post-hire outcomes is exhibited;

reducing the input parameters to a subset of input parameters for use as remaining input features to a neural network, wherein the reducing comprises removing the ineffective predictors, and wherein the remaining input features comprise a mix of answers to psychological assessment questions and answers to bio-data questions; and

training a neural network with the one or more observed post-hire outcomes and the remaining input features, comprising a mix of answers to psychological assessment questions and answers to bio-data questions, to predict the one or more post-hire outcomes for a job applicant for use in a hiring recommendation based at least on pre-hire answers by the job applicant to questions corresponding to the remaining input features.