Title :
Quantile regression for workforce analytics
Author :
Ramamurthy, K.N. ; Varshney, Kush R. ; Singh, Monika
Author_Institution :
Bus. Analytics & Math. Sci. Dept., IBM Thomas J. Watson Res. Center, Yortktown Heights, NY, USA
Abstract :
Understanding the behavior of a constantly changing workforce is key to making business decisions in modern organizations. In this paper, we develop frameworks based on quantile regression to estimate the productivity and attrition profiles of employees from revenue, headcount, and incentive data. Results show the advantages of quantile-specific profiles compared to those obtained with other regression schemes.
Keywords :
personnel; productivity; regression analysis; employee attrition profiles; employee productivity estimation; headcount data; incentive data; quantile regression; revenue data; workforce analytics; Customer satisfaction; Data models; Indexes; Linear regression; Organizations; Productivity; attrition profile; productivity profile; quantile regression; workforce behavior;
Conference_Titel :
Global Conference on Signal and Information Processing (GlobalSIP), 2013 IEEE
Conference_Location :
Austin, TX
DOI :
10.1109/GlobalSIP.2013.6737097
