Personnel selection and prediction of organizational positions using data mining algorithms (case study: Mammut industrial complex)

This study aims to identify and employ qualified individuals and assign different organizational positions. Accordingly, a data mining approach is proposed. This paper presents an empirical study which has important practical application in modern human resource management. Therefore, effective features on staff selection are extracted from literature and entered into the database after expert approval respectively. Further, the impact of each feature on staff selection is determined and the ability of applied classification algorithms is compared. The results represent that the organizational position feature has a great impact on forecasting of selection or rejection. Data mining algorithms used in this study have acceptable performance based on accuracy rate, and J48 algorithm performs better comparing to other algorithms based on accuracy rate, recall, F-measure and area under Receiver Operating Characteristic (ROC) curve. Three features of background, level of education, and major are identified as effective features in association rules. Finally, an approach is presented for applying data mining algorithms in employees hiring and organizational positions assignment procedure

Keywords:

Staff selection , Organizational Position , Effective Features , Data mining