Application of a maximum classification consensus approach for construction of a group ordinal classification of applicants in employee recruitment

Abstract

With the intensification of market competition, recruiting appropriate employees has become one of the most critical factors for organisation development. In employee recruitment, it may be sufficient for recruiters to classify applicants into several ordinal classes according to their performances in various aspects, which can be regarded as an ordinal classification-based multi-criteria group decision-making (MCGDM) problem. Particularly, due to the differences in preferences, knowledge and experience, recruiters may provide substantially divergent assessments over applicants. Integrating a consensus-reaching model into employee recruitment process is an efficient way to improve the quality of employee recruitment and avoid individual biases. To this end, this study proposes an ordinal classification consensus-based employee recruitment framework. In the proposed framework, an information violation-based maximum ordinal classification consensus model (IVMOCCM) is presented to obtain the ordinal classification of applicants. Then, an ordinal classification consensus reaching model with minimum adjustments (OCCRMMA) is developed to improve the ordinal classification consensus level among all recruiters, and this is done by minimising the distance between original assessments and reassessments over applicants. Further, an interactive employee recruitment process with ordinal classification consensus is designed. Finally, some theoretical analyses, an application case and a detailed comparative analysis are conducted to demonstrate the validity of the proposal.

Keywords:

• Employee recruitment
• multi-criteria group decision making
• ordinal classification consensus
• information violation
• minimum adjustment

Disclosure statement

No potential conflict of interest was reported by the authors.

Funding

This work was supported by the Grants (Nos. 72171075, 71801081, and 71971149) from National Natural Science Foundation (NSF) of China.