Abstract
This paper describes the use of a machine-learning technique to derive executive compensation planning rules. The specific learning technique was AQ15, which constructs rules by classifying sample data according to features or characteristics. The validity of the resulting rules was tested by obtaining a measure of performance called an estimate of the error rate. The machine-derived rules were then compared to rules made by human experts and by two other versions of AQ15. Although not statistically significant, the machine-learning version of AQ15 using hypotheses from human experts outperformed the other methods of rule construction.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Intelligent Systems in Accounting, Finance and Management
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
