A machine learning based decision support system for predicting employee turnover and remaining life in organization İşgücü devir hızı ve kurumda kalan vade tahmini için makine öğrenmesi temelli karar destek sistemi
Journal of the Faculty of Engineering and Architecture of Gazi University, cilt.41, sa.2, ss.967-980, 2026 (SCI-Expanded, Scopus, TRDizin)
- Yayın Türü: Makale / Tam Makale
- Cilt numarası: 41 Sayı: 2
- Basım Tarihi: 2026
- Doi Numarası: 10.17341/gazimmfd.1562904
- Dergi Adı: Journal of the Faculty of Engineering and Architecture of Gazi University
- Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Art Source, Compendex, TR DİZİN (ULAKBİM), Academic Search Ultimate (EBSCO), Engineering Source (EBSCO)
- Sayfa Sayıları: ss.967-980
- Anahtar Kelimeler: decision support system, employee attrition, human resource analytics, Machine learning, remaining life in organization
- Açık Arşiv Koleksiyonu: AVESİS Açık Erişim Koleksiyonu
- Erciyes Üniversitesi Adresli: Evet
Özet
Nowadays, employee turnover has become an important problem for many businesses and is a cause of concern for human resource management and the sustainability of production. It is known in the literature that the unplanned departure of a skilled employee negatively affects operational efficiency, workload balance, and employee motivation. It is necessary to estimate how long the employees will continue to work in the organization (remaining productive working time/life). This prediction will be a guide for promotions and incentives to be given to the employee. In this study, our aim is to create a decision support system that will enable the sustainable management of employee turnover. In this direction, businesses/decision makers can monitor the effects of social, psychological, physiological, and cultural factors of their employees on labor turnover and develop a proactive approach by using the decision support system. In this study, blue-collar employees who left their jobs in the last 10 years in the production department of a large-scale furniture manufacturer were analyzed. A pool of factors that may affect employee turnover was created, and attributes that can be obtained from business data sources were selected. The data obtained from the system were statistically analyzed. Using machine learning techniques, models were built to predict the reason for the employee's leave and the day he/she will spend in the organization. A decision support system has been designed to receive data from the system as input, perform statistical analysis and prediction, and provide warnings for existing critical personnel.