View in EDS

Predictive analytics in human resource recruitment: A comparative study of machine learning algorithms.

Saved in:
Bibliographic Details
Title: Predictive analytics in human resource recruitment: A comparative study of machine learning algorithms.
Authors: Singh, Niharika1 (AUTHOR) niharika_singh14@yahoo.co.in, Chakraborty, Sudeshna2 (AUTHOR) sudeshna2529@gmail.com
Source: AIP Conference Proceedings. 2025, Vol. 3297 Issue 1, p1-11. 11p.
Subject Terms: *MACHINE learning, *COMPARATIVE studies, *EMPLOYEE selection, *PREDICTION models, *MODEL validation, *EMPLOYEE recruitment, *HUMAN resources departments
Abstract: Through a comparison of machine learning algorithms, this abstract provides a thorough investigation of the use of predictive analytics in HR recruitment. Organisations are increasingly using advanced analytics to improve their recruitment operations in the ever-changing talent acquisition landscape. The goal of this study is to compare how well different machine learning algorithms predict the results of successful candidates. Using a comparative methodology, the paper examines the effectiveness of well-known machine learning algorithms, including Random Forest, Support Vector Machines, Neural Networks, and Gradient Boosting. Model training and assessment are based on a heterogeneous dataset that includes past recruiting data, including candidate traits, interview performance, and subsequent job success measures. To give a thorough grasp of the algorithms' predictive capabilities, the research assesses them using important performance criteria like accuracy, precision, recall, and F1 score. The comparative analysis's findings illuminated each algorithm's advantages and disadvantages with regard to hiring human resources. The results are intended to assist organisations in choosing the best machine learning strategy for their unique hiring requirements. The study also looks into how interpretable the models are, taking responsibility and openness into account when making hiring-related decisions. This study has practical consequences for HR professionals and decision-makers who want to use predictive analytics to optimise and streamline their recruitment processes. Its implications go beyond the academic domain. In the end, this study adds to the current conversation about the incorporation of cutting-edge technology into HRM and lays the groundwork for further developments in the area of predictive analytics in hiring. [ABSTRACT FROM AUTHOR]
Database: Academic Search Index
Description
Abstract:Through a comparison of machine learning algorithms, this abstract provides a thorough investigation of the use of predictive analytics in HR recruitment. Organisations are increasingly using advanced analytics to improve their recruitment operations in the ever-changing talent acquisition landscape. The goal of this study is to compare how well different machine learning algorithms predict the results of successful candidates. Using a comparative methodology, the paper examines the effectiveness of well-known machine learning algorithms, including Random Forest, Support Vector Machines, Neural Networks, and Gradient Boosting. Model training and assessment are based on a heterogeneous dataset that includes past recruiting data, including candidate traits, interview performance, and subsequent job success measures. To give a thorough grasp of the algorithms' predictive capabilities, the research assesses them using important performance criteria like accuracy, precision, recall, and F1 score. The comparative analysis's findings illuminated each algorithm's advantages and disadvantages with regard to hiring human resources. The results are intended to assist organisations in choosing the best machine learning strategy for their unique hiring requirements. The study also looks into how interpretable the models are, taking responsibility and openness into account when making hiring-related decisions. This study has practical consequences for HR professionals and decision-makers who want to use predictive analytics to optimise and streamline their recruitment processes. Its implications go beyond the academic domain. In the end, this study adds to the current conversation about the incorporation of cutting-edge technology into HRM and lays the groundwork for further developments in the area of predictive analytics in hiring. [ABSTRACT FROM AUTHOR]
ISSN:0094243X
DOI:10.1063/5.0286286