We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
MACHINELEARNINGALGORITHM TO PREDICT AND IMPROVE EFFICIENCY OF EMPLOYEE PERFORMANCE IN ORGANIZATIONS.
- Authors
Banu, Sohara; Agarwal, Nipun; Singh, Akhil; Shaik, Sobiya; Nikitha, P. Sai
- Abstract
Employee performance has been identified as a critical problem for companies because of its negative effect on operational productivity and long period evolution plans. To solve this problem, companies use machine learning algorithms to anticipate workplace efficiency. Precise forecasts enable organizations to act on preservation or succession planning of employees. However, the data for the modeling issue originates from HR Information Systems; It is generally less in relation to other areas of the companies information systems and is clearly relevant to its objectives This contributes to the presence of redundant values in the data that makes predictive models vulnerable to over-fitting and thus unreliable. This is the central subject based on in this article, and one that has not been discussed conventionally. Using HRIS data from a global retailer, XGBoost is calculated against six widely used supervised classification method and reveals its considerably higher precision for employee performance estimation
- Publication
International Journal of Advanced Research in Computer Science, 2020, Vol 11, p6
- ISSN
0976-5697
- Publication type
Academic Journal