Document Type : Original Research
Authors
1
PhD Candidate, Group of Information Technology Management, Faculty of Technology and Industrial Management, College of Management, University of Tehran, Tehran, Iran.
2
Associate Professor, Group of Information Technology Management, Faculty of Technology and Industrial Management, College of Management, University of Tehran, Tehran, Iran.
3
Associate Professor, Group of Leadership and Human Capital, Faculty of Public Administration and Organization Science, College of Management, University of Tehran, Tehran, Iran.
4
Professor, Group of Information Technology Management, Faculty of Technology and Industrial Management, College of Management, University of Tehran, Tehran, Iran.
10.48311/ormr.2025.107371.0
Abstract
In the evolving landscape of human resource management, competency models serve as a crucial tool for aligning human resource development with an organization's strategic goals, particularly in managerial roles. Although management competency models have been developed since 1990, conventional approaches to designing competency models and assessments based on these models have faced challenges in terms of what constitutes competency, the relationship between competencies and superior performance, and the method of model development, which is often based on expert judgment and qualitative assessments, and therefore are subjective experiences and judgments. To address these challenges, this study proposes a data mining-based framework for developing competency models for managers.
This framework has been developed through deductive qualitative content analysis of 25 studies identified through a systematic literature review, based on the standard process for data mining, CRISP-DM. 25 studies that employed data mining techniques at various stages of competency model design for managers used to identify and integrate common patterns. As a result of qualitative content analysis, 16 categories were obtained, of which 12 categories, including competency clustering, clustering individuals based on performance, interpretation of performance clusters and identification of superior performance cluster, classification algorithms for establishing a relationship between competency and performance, interpretation of the model, and specifying the rules related to competencies, are presented in the form of a framework for designing competency model, and 4 categories also help to complete the framework and use it. Accordingly, this framework enables the design of more objective and data-driven models.
Keywords
Subjects
