پیش‌بینی ترک شغل و عوامل فردی و سازمانی مؤثر بر آن با استفاده از روش‌های یادگیری ماشین

نوع مقاله : مقاله پژوهشی

نویسندگان

دانشکده اقتصاد، دانشگاه خوارزمی، تهران، ایران.

چکیده

هدف: این مقاله در نظر دارد تا با تجزیه و تحلیل داده‌های مرتبط با نیروی کار یک فروشگاه‌های زنجیره‌ به پیش‌بینی ترک شغل نیروها و بررسی عوامل فردی و سازمانی (شغلی) موثر بپردازد. 
روش‌شناسی: تعداد 17542رکورد اطلاعاتی منحصر به فرد شامل اطلاعات وضعیت فعالیت فرد (ادامه فعالیت یا ترک شغل) و 12 مشخصه فردی و شغلی در بازه زمانی آبان 1398 الی 1401 بکار گرفته شد و سپس به روش داده‌کاوی و با استفاده از الگوریتم‌های یادگیری ماشین درخت تصمیم و ماشین بردار پشتیبان (SVM) به پیش‌بینی ترک شغل نیروی کار در این فروشگاه زنجیره‌ای بصورت پایلوت در سراسر کشور پرداخته شد.
یافته‌ها: نتایج بدست آمده نشان دادند که ویژگی‌ها و مشخصه‌های شغلی تأثیر بیشتری بر ترک شغل دارند. بطور مشخص، از بین ویژگی‌های مختلف تعداد جابجایی نیروها، سمت سازمانی (صف یا ستادی)، سنوات خدمت و ساعت‌کار بیشترین اهمیت و تأثیرگذاری را بر ترک شغل دارند. از میان مشخصه‌های فردی نیز مشاهده شد که ترک شغل در میان جوانان و افراد کمتر از 30 سال سن بیشتر است. بر اساس این ویژگی‌ها، مدل‌های ماشین بردار پشتیبان (SVM) با دقت 91 درصد و امتیاز-F1 بالای 90 درصد و الگوریتم درخت تصمیم نیز با دقت 83 درصد و امتیاز-F1 به همین اندازه از عملکرد مناسبی در دسته‌بندی و پیش‌بینی موارد ترک شغل برخوردار شدند.
نتیجه‌گیری: می‌توان بر اساس مشخصه‌های فردی و شغلی و با استفاده از روش‌های داده‌کاوی و یادگیری ماشینی سیاست‌هایی در جهت حفظ و نگه‌داشت منابع انسانی تنظیم کرد که موجب کاهش هزینه‌ها و همچنین حفظ مزیت‌های رقابتی و پیشرفت و توسعه بنگاه خواهد شد.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

The Prediction of Employee Turnover and its Personal and Organizational Determinants Using Machine Learning Methods

نویسندگان [English]

  • Abbas Khandan
  • Soheila Mohammadi
Faculty of Economics, University of Kharazmi, Tehran, Iran.
چکیده [English]

This study analyzing the chain stores’ personnel data intends to predict the employees’ turnover rate and examine its personal and organizational (occupational) determining factors. A dataset of 17542 records including information of personnel's activity status (active or quit) and 12 personal and occupational characteristics in the period of November 2018 to 2014 are used in machine learning algorithms of decision tree and support vector machine (SVM) to predict the workforce turnover rate across the country in a pilot chain store. The results show that job characteristics have a greater effect on employees’ turnover. Specifically, among different characteristics, four factors of personnel transfers, their organizational position (line or staff), years of service and working hours have the most importance and influence on job turnover. Among the individual characteristics, it was also observed that job quit is more prevalent among young people with less than 30 years old. Based on these characteristics, support vector machine (SVM) model with 91% accuracy and F1-score above 90% and decision tree algorithm with 83% accuracy and F1-score have shown a good performance in classification and prediction of employees’ turnover. Based on personal and job characteristics and using data mining and machine learning methods, organizations can set policies to preserve human resources, which will reduce costs and also maintain their competitive advantages necessary for the progress and development of the company.

کلیدواژه‌ها [English]

  • Classification
  • Determinants
  • Employee Turnover
  • Individual and Occupational Machine Learning

Abedin, B., Akbari Emami, S., & Abbasnejad, T. (2020). Designing a Conceptual Model of Talent Turnover among Iranian Organizations: An Exploratory Research in the ICT Industry. Journal of Sustainable Human Resource Management2(2), 49-64. [In Persian].

Al Akasheh, M., Faisal Malik, E., Hujran, O., & Zaki, N. (2024). A Decade of Research on Machine Learning Techniques for Predicting Employee Turnover: A Systematic Literature Review. Expert Systems with Applications, 238, Retrieved from https://doi.org/10.1016/j.eswa.2023.121794.

Alirahimi M. M., Amirkhani A., & Rasouli R. (2018). Designing a Model for Turnover Reduction in Iranian Oil Terminals Company (IOTC). Strategic Studies in the Oil and Energy Industry, 9(34), 53-82. [In Persian].

Alsagheer, R. H., Alharan, A. F., & Al-Haboobi, A. S. (2017). Popular Decision Tree Algorithms of Data Mining Techniques: A Review. International Journal of Computer Science and Mobile Computing, 6(6), 133-142.

Amiri, G. and Mahmoudzadeh, S. M. (2015). The Examination Factors Affecting the Reduction of Employee Turnover in the Iranian Public Organizations. Case Study: Ministry of Road and Urban Development (Center Staff). Organizational Culture Management13(2), 559-579. [In Persian].

Arefi S., Sarkhosh S., & Raoofi S. (2019). Explanation of the Effective Factors of Job Leave from Nurses' Point of View: A Qualitative Study. Health Based Research, 5(1), 13-28. [In Persian].

Arokiasamy, A. R. A. (2013). A Qualitative Study on Causes and Effects of Employee Turnover in the Private Sector in Malaysia. Middle-East Journal of Scientific Research, 16(11), 532-1541.

Bassok, D., Markowitz, A. J., Bellows, L., & Sadowski, K. (2021). New Evidence on Teacher Turnover in Early Childhood. Educational Evaluation and Policy Analysis, 43(1), 172-180.

Brownlee, J. (2020). Data Preparation for Machine Learning-Data Cleaning, Feature Selection and Data Transformation in Python: Machine Learning Mastery. Retrieved from https://www.machinelearningmastery.com/data-preparation-for-machine-learning/.

Chauhan, V. K., Dahiya, K., & Sharma, A. (2019). Problem Formulations and Solvers in Linear SVM: A Review. Artificial Intelligence Review, 52(2), 803-855.

Cheshmbarah, E. (2018). Study of Factors Affecting Employee Turnover (Master's Thesis). Islamic Azad University, Bandar Abbas. [In Persian].

Chowdhury, S., Joel-Edgar, S., Dey, P. K., Bhattacharya, S., & Kharlamov, A. (2022). Embedding Transparency in Artificial Intelligence Machine Learning Models: Managerial Implications on Predicting and Explaining Employee Turnover. The International Journal of Human Resource Management, 34(14), 2732–2764.

Dabbashi, F., Nouri, A., Oreyzi, H., & Dibaji, S. M. (2015). Predicting Employees' Turnover Intention by Individual, Occupational and Organizational Factors. Knowledge & Research in Applied Psychology, 17(2), 45-54. [In Persian].

Dulaty, H., & Deyhimpuor, M. (2018). An Assessment of Factors Affecting Organizational Trauma on Leaving Service by Military Personnel. Journal of Research in Human Resources Management9(4), 81-106. [In Persian].

Dunegan, K. (1993). Framing, Cognitive Modes, and Image Theory: Toward an Understanding of a Glass Half Full, Journal of Applied Psychology, 78(3), 491-503.

Elaine, M. (1997). Job Tenure Shift for Men and Women. HR Magazine, 42(50), 1-20.

Hashemzehi R., Najafbeygi R., & Zabihi M. (2021). Designing the Model of Knowledge Workers Turnover in Khorasan Razavi Oil Products Distribution Company. Strategic Studies in the Oil and Energy Industry, 12(47), 22-39. [In Persian]

Healy, M. C., Lehman, M., & McDaniel, M. A. (1995). Age and Voluntary Turnover: A Quantitative Review. Personnel Psychology, 48(2), 335–345.

Marsh, R. M., & Mannari, H. (1977). Organizational Commitment and Turnover: A Prediction Study. Administrative Science Quarterly, 22(1), 57–75.

McDermid, F., Mannix, J., & Peters, K. (2020). Factors Contributing to High Turnover Rates of Emergency Nurses: A Review of the Literature. Australian Critical Care, 33(4), 390-396.

Park, J., Feng, Y. & Jeong, SP. Developing an Advanced Prediction Model For New Employee Turnover Intention Utilizing Machine Learning Techniques. Scientific Reports, 14, Retrieved from https://doi.org/10.1038/s41598-023-50593-4.

Phillips, D. R., & Roper, K. O. (2009). A Framework for Talent Management in Real Estate. Journal of Corporate Real Estate, 11(1), 7-16.

Pirayesh, R., Mohammadi, M., & Badfar, I. (2019). Factors Affecting Employees' Intention to Leave and Its Impact on Employee Performance in Zarrin Roy Zanjan Company. Applied Studies in Management and Development Sciences, 5(1), 7-19. [In Persian].

Rokach, L., & Maimon, O. Z. (2014). Data Mining With Decision Trees: Theory and Applications. Singapore: World Scientific Publishing Co.

Summers, T. P., & Hendrix, W. H. (1991). Modelling the Role of Pay Equity Perceptions: A Field Study. Journal of Occupational Psychology, 64, 145-157.

Taleghani, G., Abdolmaleki, J., and Ghafari, A. (2016). The Investigation of the Individual Factors on Turnover Intention of Employees in Education Administration of Kurdistan Province. Journal of Public Administration8(1), 219-232. [In Persian].

Waldman, J. D., Kelly, F., Aurora, S., & Smith, H. (2004). The Shocking Cost of Turnover in Health Care, Health Care Management Review, 29(1), 2-7.

Yun, M. R., & Yu, B. (2021). Strategies for Reducing Hospital Nurse Turnover in South Korea: Nurses' Perceptions and Suggestions. Journal of Nursing Management, 29(5), 1256-1262.

Zabani Shadabad, M. A., Hassani, M., & Ghasemzadeh, A. (2017). The Relationship between Job Engagement & Job Propriety with Professional Ethics & Intent to Leave. Ethics in Science and Technology, 12 (2). 77-84. [In Persian].

Zhao, Y., Hryniewicki, M. K., Cheng, F., Fu, B., & Zhu, X. (2018). Employee Turnover Prediction with Machine Learning: A Reliable Approach. In Proceedings of SAI Intelligent Systems Conference. Cham: Springer.