Leveraging Machine Learning Methods for Predicting Employee Turnover Within the Framework of Human Resources Analytics

Öz

Employee turnover is a critical challenge for organizations, leading to significant costs and disruptions. This study aims to leverage Machine Learning (ML) techniques within the framework of Human Resources Analytics (HRA) to predict employee turnover effectively. The research evaluates and compares the performance of six widely used models: Decision Trees, Support Vector Machines (SVM), Logistic Regression, Random Forest, XGBoost, and Artificial Neural Networks. These models were implemented using the R programming language on an open-source dataset from IBM. The methodology involved data preprocessing, splitting into training, validation and testing sets, model training, and performance evaluation using metrics such as accuracy, sensitivity, specificity, precision, F1-score, and ROC-AUC. The results indicate that the Logistic Regression model outperformed the other models, achieving high accuracy and a good F1-score. The study concludes by emphasizing the importance of HRA and ML techniques in predicting and managing employee turnover, while discussing limitations such as class imbalance and the need for more rigorous performance evaluation. Future research directions include exploring alternative models, feature selection techniques, and addressing class imbalance.

Anahtar Kelimeler

• Human Resources Analytics
• Employee Turnover Prediction
• Machine Learning Models

Makine Öğrenimi Yöntemlerini İnsan Kaynakları Analitiği Çerçevesinde İşten Ayrılma Tahminleri için Kullanma

Öz

Çalışan devir oranı, kuruluşlar için önemli bir zorluk oluşturmakta ve önemli maliyetlere ve aksaklıklara yol açmaktadır. Bu çalışma, insan kaynakları analitiği çerçevesinde makine öğrenimi tekniklerini etkin bir şekilde kullanarak çalışan devirini öngörmeyi amaçlamaktadır. Araştırma, altı yaygın olarak kullanılan modelin performansını değerlendirmekte ve karşılaştırmaktadır: Karar Ağaçları, Destek Vektör Makineleri, Lojistik Regresyon, Rastgele Orman, XGBoost ve Yapay Sinir Ağları. Bu modeller, IBM'den açık kaynaklı bir veri kümesi üzerinde R programlama dili kullanılarak uygulanmıştır. Çalışmanın metodlolojisi, veri ön işleme, eğitim, doğrulama ve test setlerine bölme, model eğitimi ve doğruluk, hassasiyet, özgünlük, hassasiyet, F1-skoru ve ROC-AUC gibi ölçümleri kullanarak performans değerlendirmeyi içermektedir Sonuçlar, Lojistik Regresyon modelinin diğer modellerden daha iyi bir performans sergilediğini, yüksek doğruluk ve iyi bir F1-skoru elde ettiğini göstermektedir. Çalışma kasapmında, çalışan devir oranını öngörmek ve yönetmek için insan kaynakları analitiği ve makine öğrenmesi tekniklerinin önemi vurgulanarak, sınıf dengesizliği gibi sınırlamaları ve daha güvenilir performans değerlendirmesi gereksinimine yönellik tartışmalara da yer vermektedir. Çalışmanın son kısmında, gelecek araştırma konuları çerçevesinde alternatif modellerin keşfedilmesi, özellik seçim teknikleri kullanılarak sonuçların değerlendirilmesi ve sınıf dengesizliğini gidermeye dönük hususlar ele alınmaktadır.

Anahtar Kelimeler

• İnsan kaynakları analitiği
• Çalışan devir hızı tahmini
• Makine öğrenimi modelleri.

Kaynakça

1. Aarons, G., Sawitzky, A., 2006. Organizational climate partially mediates the effect of culture on work attitudes and staff turnover in mental health services. Administration and Policy in Mental Health and Mental Health Services Research, 33(3), 289-301. https://doi.org/10.1007/s10488-006-0039-1
2. Akter, S., Wamba, S. F., Gunasekaran, A., Dubey, R., Childe, S. J., 2016. How to improve firm performance using big data analytics capability and business strategy alignment? International Journal of Production Economics, 182, 113–131. https://doi.org/10.1016/j.ijpe.2016.08.018
3. Alan, A., 2020. Makine Öğrenmesi Sınıflandırma Yöntemlerinde Performans Metrikleri ile Test Tekniklerinin Farklı Veri Setleri Üzerinde Değerlendirilmesi (Yüksek Lisans Tezi). Fırat Üniversitesi, Fen Bilimleri Enstitüsü, s.19
4. Alsaadi, E., Khlebus, S., Alabaichi, A., 2022. Identification of Human Resoıurce Analytics using MLalgorithms. Telkomnika (Telecommunication Computing Electronics and Control), 20(5), 1004. https://doi.org/10.12928/telkomnika.v20i5.21818
5. Ashworth, M., 2006. Preserving knowledge legacies: workforce aging, turnover and human resource issues in the us electric power industry. The International Journal of Human Resource Management, 17(9), 1659-1688. https://doi.org/10.1080/09585190600878600
6. Avrahami, D., Pessach, D., Singer, G., Ben‐Gal, H. C., 2022. A human resources analytics and machine-learning examination of turnover: implications for theory and practice. International Journal of Manpower, 43(6), 1405-1424. https://doi.org/10.1108/ijm-12-2020-0548
7. Bahadır, M. B., Bayrak, A. T., Yücetürk, G., Ergun, P., 2021. A Comparative Study for Employee Churn, Prediction, Researchgate, 1-4.
8. Balcıoğlu, Y. S., Artar, M., 2022. Çalışanların İşten Ayrılma Olasılığının Makine Öğrenmesi İle Tahmini: K-En Yakın Komşu Algoritması İle. Güncel İşletme, Yönetim ve Muhasebe Çalışmaları, 29-35. https://www.researchgate.net/publication/359362785

9. Bardoel, A., Russell, G., Advocat, J., Mayson, S., Kay, M., 2020. Turnover among australian general practitioners: a longitudinal gender analysis. Human Resources for Health, 18(1). https://doi.org/10.1186/s12960-020-00525-4
10. Barın, H. D., 2022. Employee Turnover Probability Prediction, A thesis submitted to the Graduate School of Engineering and Science of Bilkent University for the degree of Master of Science in Industrial Engineering, 1-75.
11. Belbin, C., Erwee, R., Wiesner, R., 2012. Employee perceptions of workforce retention strategies in a health system. Journal of Management & Organization, 18(5), 742-760. https://doi.org/10.5172/jmo.2012.18.5.742
12. Bogaert, K., Leider, J., Castrucci, B., Sellers, K., Whang, C., 2019. Considering leaving, but deciding to stay: a longitudinal analysis of intent to leave in public health. Journal of Public Health Management and Practice, 25(2), S78-S86. https://doi.org/10.1097/phh.0000000000000928
13. Breiman, L., 2001. Rastgele Ormans. Machine learning, 45(1), 5-32.
14. Catani F, Lagomarsino D, Segoni S, Tofani V., 2013. Landslide susceptibility estimation by Rastgele Ormans technique: sensitivity and scaling issues. Nat Hazards Earth Syst Sci, 13:2815–2831, doi:10.5194/nhess-13-2815-2013.
15. Chapman, G., Nasirov, S., Özbilgin, M., 2022. Workforce diversity, diversity charters and collective turnover: long‐term commitment pays. British Journal of Management, 34(3), 1340-1359. https://doi.org/10.1111/1467-8551.12644
16. Chaudhary, M., 2022. Rationale of employee turnover: an analysis of banking sector in nepal. International Research Journal of MMC, 3(2), 18-25. https://doi.org/10.3126/irjmmc.v3i2.46291
17. Chisholm, M., Russell, D., Humphreys, J., 2011. Measuring rural allied health workforce turnover and retention: what are the patterns, determinants and costs?. Australian Journal of Rural Health, 19(2), 81-88. https://doi.org/10.1111/j.1440-1584.2011.01188.x
18. Choi, J., Ko, I., Kim, J., Jeon, Y., Han, S., 2021. MLframework for multi-level classification of company revenue. Ieee Access, 9, 96739-96750. https://doi.org/10.1109/access.2021.3088874
19. Demir, K., Çalık, E., 2021. İnsan Kaynakları Analitiği: Modelleme ve Örnek Uygulamalarla. 2. Baskı, Nobel Bilimsel Yayıncılık.
20. Emmanuel-Okereke, I. L., Anigbogu, S. O., 2022. Predicting the Perceived Employee Tendency of Leaving an Organization Using SVM and Naive Bayes Techniques. Open Access, 1-15.
21. Erkal, H., Keçecioğlu, T., Yılmaz, M. K., 2014. Gelecek 10 Yıl İçerisinde İnsan Kaynaklarının Yüzleşeceği Zorluklar. EUL Journal of Social Sciences, V(II), LAÜ Sosyal Bilimler Dergisi, Aralık, 32-63.
22. Gallup., 2023. State of the Global Workplace Report - Gallup. Gallup.com. Retrieved February 21, 2024, from https://www.gallup.com/workplace/349484/state-of-the-global-workplace.aspx#ite-506924
23. Gao, X., Wen, J., Zhang, C., 2019. An improved random forest algorithm for predicting employee turnover. Mathematical Problems in Engineering, 2019, 1-12. https://doi.org/10.1155/2019/4140707
24. Hatch‐Maillette, M., Harwick, R., Baer, J., Masters, T., Cloud, K., Peavy, M., Wells, E., 2019. Counselor turnover in substance use disorder treatment research: observations from one multisite trial. Substance Abuse, 40(2), 214-220. https://doi.org/10.1080/08897077.2019.1572051
25. Healy, K., Oltedal, S., 2010. An institutional comparison of child protection systems in australia and norway focused on workforce retention. Journal of Social Policy, 39(2), 255-274. https://doi.org/10.1017/s004727940999047x
26. https://www.kaggle.com/datasets/pavansubhasht/ibm-hr-analytics-attrition-dataset?resource=download
27. Jain, P. K., Jain, M., Pamula, R., 2020. Explaining and Predicting Employees' Attrition: A MLApproach. Research Article, 1-11.
28. Judrups, J., Cinks, R., Birzniece, I., Andersone, I., 2021. MLbased solution for predicting voluntary employee turnover in organization.. https://doi.org/10.22616/erdev.2021.20.tf296
29. Karcı, Z., 2017. Lojistik Regresyon Modeli ile Elde Edilen Tahminlerin ROC Eğrisi Yardımıyla Değerlendirilmesi: Türkiye'de Hanehalkı Yoksulluğu Üzerine Bir Araştırma (Yüksek Lisans Tezi). T.C. Süleyman Demirel Üniversitesi Sosyal Bilimler Enstitüsü, Ekonometri Anabilim Dalı, Isparta, 46.
30. Kışaoğlu, Z. Ö., 2014. Employee Turnover Prediction Using MLBased Methods, A thesis submitted to the Graduate School of Natural and Applied Sciences of Middle East Technical University.
31. Kropp, B., McRae, E. R., 2022. 11 Trends that Will Shape Work in 2022 and Beyond, 11 Trends that Will Shape Work in 2022 and Beyond (hbr.org)
32. Kutlugün, M. A., Çakır, M. Y., Kiani, F., 2017. Yapay Sinir Ağları ve K-En Yakın Komşu Algoritmalarının Birlikte Çalışma Tekniği (Ensemble) ile Metin Türü Tanıma, 2 https://www.researchgate.net/publication/323990877.
33. Liao, C., 2023. Employee turnover prediction using MLmodels.. https://doi.org/10.1117/12.2672733
34. Liu, H. and Liu, Y., 2021. Visualization research and analysis of turnover intention. E3s Web of Conferences, 253, 02018. https://doi.org/10.1051/e3sconf/202125302018
35. Maharjan, R., 2021. Employee Churn Prediction using Logistic Regression and Support Vector Machine, San Jose State University, Master's Projects. DOI: https://doi.org/10.31979/etd.3t5h-excq.
36. Maisuradze, M., 2017. Predictive analysis on the example of employee turnover (Master's thesis). Tallinn University of Technology, Faculty of Information Technology, Department of Computer Systems, 3-76.
37. Mayson, S., Bardoel, A., 2021. Sustaining a career in general practice: embodied work, inequality regimes, and turnover intentions of women working in general practice. Gender Work and Organization, 28(3), 1133-1151. https://doi.org/10.1111/gwao.12659
38. McCarthy, A., Moonesinghe, R., Dean, H., 2020. Association of employee engagement factors and turnover intention among the 2015 u.s. federal government workforce. Sage Open, 10(2), 215824402093184. https://doi.org/10.1177/2158244020931847
39. Moturi, D. G., Wekesa, S., Juma, D., 2023. Influence of self efficacy on employee acceptance levels and use of human resource analytics in microfinance institutions in kenya. International Journal of Business Management, Entrepreneurship and Innovation, 5(1), 31-50. https://doi.org/10.35942/jbmed.v5i1.304
40. Onnis, L., 2017. Human Resourse Management policy choices, management practices and health workforce sustainability: remote australian perspectives. Asia Pacific Journal of Human Resources, 57(1), 3-23. https://doi.org/10.1111/1744-7941.12159
41. Pavansubhash, 2016. IBM HR Analytics Employee Attrition & Performance
42. Peryön., 2018. Çalişan Devir Orani Araştirmasi Sonuç Raporu. In https://www.peryon.org.tr/upload/files/PERYO%CC%88N_C%CC%A7al%C4%B1s%CC%A7an_Devir_Oran%C4%B1_Sonuc%CC%A7_Raporu_2017-2018.pdf.
43. Poku, C., Alem, J., Poku, R., Osei, S., Amoah, E., Ofei, A., 2022. Quality of work-life and turnover intentions among the ghanaian nursing workforce: a multicentre study. Plos One, 17(9), e0272597. https://doi.org/10.1371/journal.pone.0272597
44. Putri, M. and Rachmawati, R., 2022. Psychological contract, employee engagement, and perceived organizational support influence on employee turnover intention in pharmaceutical industry.. https://doi.org/10.4108/eai.27-7-2021.2316894
45. Randstad., 2022. Randstand Trends 2022 Report. In https://www.randstad.gr/. Retrieved February 21, 2024, from https://www.randstad.gr/s3fs-media/gr/public/2022-07/hr-trends-2022-salary-report-eng.pdf
46. Randstad., 2023. Randstand Trends 2023 Report. In https://www.randstad.com.tr/. Retrieved February 21, 2024, from https://www.randstad.com.tr/s3fs-media/tr/public/2023-04/TR_Turkey%20HR%20Trends%202023_0.pdf
47. Ribes, E., Touahri, K., Perthame, B., 2017. Employee turnover prediction and retention policies design: a case study, 1-10.
48. Roche, A., McEntee, A., Kostadinov, V., Hodge, S., Chapman, J., 2021. Older workers in the alcohol and other drug sector: predictors of workforce retention. Australasian Journal on Ageing, 40(4), 381-389. https://doi.org/10.1111/ajag.12917
49. Rokach, L., Maimon, O., 2005. Decision Trees. In O. Maimon & L. Rokach (Eds.), Data Mining and Knowledge Discovery Handbook (pp. 165-192). Springer US. https://doi.org/10.1007/0-387-25465-X_9
50. Russell, D., Zhao, Y., Guthridge, S., Ramjan, M., Jones, M., Humphreys, J. Wakerman, J., 2017. Patterns of resident health workforce turnover and retention in remote communities of the northern territory of australia, 2013–2015. Human Resources for Health, 15(1). https://doi.org/10.1186/s12960-017-0229-9
51. Scanlan, J., Meredith, P., Poulsen, A., 2013. Enhancing retention of occupational therapists working in mental health: relationships between wellbeing at work and turnover intention. Australian Occupational Therapy Journal, 60(6), 395-403. https://doi.org/10.1111/1440-1630.12074
52. Schlechter, A., Syce, C., Bussin, M., 2016. Predicting voluntary turnover in employees using demographic characteristics: a south african case study. Acta Commercii, 16(1). https://doi.org/10.4102/ac.v16i1.274
53. Shanthakumara, A. H., Divya, J., Harshitha, H. T., Pallavi, L. V., Spoorthy, B. C. S., 2022. Prediction of Employee Turnover using Machine Learning. Grenze Scientific Society, 1-13.
54. Shrivastava, S., Nagdev, K., Rajesh, A., 2017. Redefining HR using people analytics: the case of Google. Human Resourse Management International Digest, 1-4.
55. Stachová, K., Baroková, A., Stacho, Z., 2021. Optimization of Employee Turnover through Predictive Analysis, Institut of Management, University of Ss. Cyril and Methodius in Trnava, Slovakia. Faculty of Management, Comenius University, Bratislava, Slovakia.
56. State of the Global Workplace Report - Gallup., 2024. Gallup.com. https://www.gallup.com/workplace/349484/state-of-the-global-workplace.aspx#ite-506924
57. Uzak, B., 2022. Telekomünikasyon Sektöründe Çalışan Kaybı Tahmini İçin Makine Öğrenmesi Modeli Seçimi (Yüksek Lisans Tezi). T.C. Bursa Uludağ Üniversitesi Fen Bilimleri Enstitüsü, 4-5.
58. Van Vulpen, E., 2023. What is HR Analytics? All You Need to Know to Get Started. AIHR. https://www.aihr.com/blog/what-is-hr-analytics/
59. Wijaya, D., Ds, J., Barus, S., Pasaribu, B., Sirbu, L., Dharma, A., 2021. Uplift modeling vs conventional predictive model: a reliable MLmodel to solve employee turnover. International Journal of Artificial Intelligence Research, 5(1). https://doi.org/10.29099/ijair.v4i2.169
60. Woltmann, E., Whitley, R., McHugo, G., Brunette, M., Torrey, W., Daras, L., Drake, R., 2008. The role of staff turnover in the implementation of evidence-based practices in mental health care. Psychiatric Services, 59(7), 732-737. https://doi.org/10.1176/ps.2008.59.7.732
61. Yavuz, H. V., 2016, Sanayi ve Hhizmet sektöründe işgücü devir oranlarinin yüksek olmasinin nedenleri ve çözüm önerileri: Denizli örneği (Yüksek Lisans Tezi). Pamukkale Üniversitesi Sosyal Bilimler Enstitüsü. Yüksek Lisans Tezi, Çalışma Ekonomisi ve Endüstri İlişkileri Anabilim Dalı, DENİZLİ, 5-14.
62. Ye, J., Pu, B., Guan, Z., 2019. Entrepreneurial leadership and turnover intention in startups: mediating roles of employees’ job embeddedness, job satisfaction and affective commitment. Sustainability, 11(4), 1101. https://doi.org/10.3390/su11041101
63. Yedida, R., Reddy, R., Vahi, R., J, R., Abhilash, Kulkarni, D., 2018. Employee Attrition Prediction, https://www.academia.edu/73094870/Employee_Attrition_Prediction, 1-3.
64. Zhu, Q., Shang, J., Cai, X., Jiang, L., Liu, F., Qiang, B., 2019. CoxRF: Employee Turnover Prediction based on Survival Analysis. In Proceedings of the 2019 IEEE, 1123-1130.