INTEGRATION OF CNN BASED DEEP LEARNING AND MACHINE LEARNING TECHNIQUES: A NOVEL METHODOLOGY IN JOB SEPARATION PREDICTIONS

Yıl 2025, Cilt: 21 Sayı: 1, 161 - 198, 26.03.2025

Yunus Emre Gür , Cem Ayden

Öz

Labor turnover leads to significant cost and productivity losses for organizations. This paper presents an innovative approach that goes beyond traditional statistical models and integrates machine learning and deep learning techniques to improve turnover prediction. By transforming the variables in the dataset into 2D QR code images, the study enables CNN-based deep learning models to perform classification on these images. This innovative step demonstrates the potential of deep learning models to analyze more complex data structures using visual data processing capabilities. After evaluating various machine learning models, the researchers performed deep learning-based feature extraction using the ResNet-18 model. Then, based on the 10 most influential features selected using the RelieF algorithm, the optimized Light Gradient Boosting (LightGBM ) model achieved excellent performance metrics of 100% accuracy, 100% precision, and 100% F1-score. These results show that this model exhibits high efficiency in turnover prediction and can make significant contributions to human resource management.

Anahtar Kelimeler

CNN-Based Deep Learning, Machine Learning, Job Separation Estimation, RelieF Feature Selection, 2D QR Transformation

CNN TABANLI DERİN ÖĞRENME VE MAKİNE ÖĞRENMESİ TEKNİKLERİNİN ENTEGRASYONU: İŞTEN AYRILMA TAHMİNLERİNDE YENİ BİR METODOLOJİ

Öz

İşgücü devri, organizasyonlar için önemli maliyet ve verimlilik kayıplarına yol açmaktadır. Bu çalışma, işten ayrılma tahminlerini geliştirmek amacıyla, geleneksel istatistiksel modellerin ötesine geçerek makine öğrenimi ve derin öğrenme tekniklerini entegre eden yenilikçi bir yaklaşım sunmaktadır. Çalışma, veri setindeki değişkenleri 2B karekod görüntülerine dönüştürmek suretiyle, CNN tabanlı derin öğrenme modellerinin bu görüntüler üzerinde sınıflandırma yapabilmesini sağlamıştır. Bu yenilikçi adım, derin öğrenme modellerinin görsel veri işleme yeteneklerini kullanarak daha karmaşık veri yapılarını analiz etme potansiyelini ortaya koymaktadır. Araştırma, çeşitli makine öğrenmesi modellerini değerlendirdikten sonra ResNet-18 modeli kullanılarak derin öğrenme tabanlı özellik çıkarımı gerçekleştirilmiştir. Daha sonra, RelieF algoritması kullanılarak seçilen en etkili 10 özelliğe dayanarak optimize edilmiş Hafif Gradyan Artırma (LighhtGBM) modeli, %100 doğruluk, %100 hassasiyet ve %100 F1-skoru gibi mükemmel performans metrikleri elde etmiştir. Bu sonuçlar, bu modelin işten ayrılma tahminlerinde yüksek etkinlik sergilediğini ve insan kaynakları yönetimi pratiğine önemli katkılarda bulunabileceğini göstermektedir.

Anahtar Kelimeler

CNN Tabanlı Derin Öğrenme, Makine Öğrenmesi, İşten Ayrılma Tahmini, RelieF Özellik Seçimi, 2B Karekod Dönüşümü

Etik Beyan

Bu çalışma için etik kurul iznine ihtiyaç duyulmamıştır.

Kaynakça

• Adeusi, K. B., Amajuoyi, P., & Benjami, L. B. (2024). Utilizing machine learning to predict employee turnover in high-stress sectors. International Journal of Management & Entrepreneurship Research, 6(5), 1702-1732. https://doi.org/10.51594/ijmer.v6i5.1143
• Adibaji, S. S., & Marleen, O. (2022). Comparative analysis of methods k-nearest neighbor, support vector machine and decision tree on prediction model of turnover intention. Journal Research of Social Science, Economics, and Management, 2(2). https://doi.org/10.59141/jrssem.v2i02.241
• Aglin, G., Nijssen, S., & Schaus, P. (2020). Pydl8.5: A library for learning optimal decision trees. Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence. https://doi.org/10.24963/ijcai.2020/750
• Al Akasheh, M., Hujran, O., Faisal Malik, E., & Zaki, N. (2024). Enhancing the prediction of employee turnover with knowledge graphs and explainable ai. IEEE Access, 12, 77041-77053. https://doi.org/10.1109/access.2024.3404829
• AlMohamed, M., AlAqeel, A., & Alkandari, K. (2022). Turnover and organizational commitment in the oil and gas industry in saudi arabia. International Journal of Research in Human Resource Management, 4(2), 01-06. https://doi.org/10.33545/26633213.2022.v4.i2a.105
• Bae, C. Y., Im, Y., Lee, J., Park, C., Kim, M., Kwon, H. U., … Kim, J. (2021). Comparison of biological age prediction models using clinical biomarkers commonly measured in clinical practice settings: Ai techniques vs. traditional statistical methods. Frontiers in Analytical Science, 1. https://doi.org/10.3389/frans.2021.709589
• Bazilevych, K., Kyrylenko, O., Parfenyuk, Y., Krivtsov, S., Meniailov, I., Kuznietcova, V., … Chumachenko, D. (2023). Comparative analysis of the machine learning models determining covid-19 patient risk levels. Radioelectronic and Computer Systems, (3), 5-17. https://doi.org/10.32620/reks.2023.3.01
• Cheng, L., Lin, C. H., Sun, C., & Wang, S. (2019). Evolutionary-fuzzy-integral-based convolutional neural networks for facial image classification. Electronics, 8(9), 997. https://doi.org/10.3390/electronics8090997
• Chivukula, R., Sajja, M. V., Lakshmi, T. J., & Harini, M. (2021). Empirical study on Microsoft malware classification. International Journal of Advanced Computer Science and Applications, 12(3). https://doi.org/10.14569/ijacsa.2021.0120361
• Conroy, S. A., Roumpi, D., Delery, J. E., & Gupta, N. (2021). Pay volatility and employee turnover in the trucking industry. Journal of Management, 48(3), 605-629. https://doi.org/10.1177/01492063211019651
• Eldora, K., Fernando, E., & Winanti, W. (2024). Comparative analysis of knn and decision tree classification algorithms for early stroke prediction: A machine learning approach. Journal of Information Systems and Informatics, 6(1), 313-338. https://doi.org/10.51519/journalisi.v6i1.664
• Feeley, T. H., & Barnett, G. A. (1997). Predicting employee turnover from communication networks. Human Communication Research, 23(3), 370-387. https://doi.org/10.1111/j.1468-2958.1997.tb00401.x
• 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
• Grebovic, M., Filipović, L., Katnić, I., Vukotic, M., & Popović, T. (2022, November). Overcoming limitations of statistical methods with artificial neural networks. In Proceedings of the 2022 International Arab Conference on Information Technology (ACIT), (1-6), IEEE. https://doi.org/10.1109/acit57182.2022.9994218
• Guo, M., & Du, Y. (2019, October). Classification of thyroid ultrasound standard plane images using ResNet-18 networks. In Proceedings of the 2019 IEEE 13th International Conference on Anti-counterfeiting, Security, and Identification (ASID), (324-328), Xiamen, China. https://doi.org/10.1109/ICASID.2019.8925267
• Harrison, S., & Gordon, P. A. (2014). Misconceptions of employee turnover: evidence-based information for the retail grocery industry. Journal of Business & Economics Research (JBER), 12(2), 145. https://doi.org/10.19030/jber.v12i2.8528
• Hasan, M. K., Sundararajan, E., Islam, S., Ahmed, F. R. A., Babiker, N. B. M., Alzahrani, A. I., ... Khan, M. A. (2024). A novel segmented random search based batch scheduling algorithm in fog computing. Computers in Human Behavior, 158, 108269. https://doi.org/10.1016/j.chb.2024.108269
• Hassanpour, M., & Malek, H. (2020). Learning document image features with squeezenet convolutional neural network. International Journal of Engineering, 33(7). https://doi.org/10.5829/ije.2020.33.07a.05
• He, K., Zhang, X., Ren, S., & Sun, J. (2016, October). Identity mappings in deep residual networks. In Proceedings of the Computer Vision–ECCV 2016: 14th European Conference Proceedings Part IV 14, (630-645), Amsterdam, The Netherlands. https://doi.org/10.48550/arxiv.1603.05027
• Hien, D. T. T., Thi, C., Kim, T., The, D., & Nguyen, C. (2020). Optimize the combination of categorical variable encoding and deep learning technique for the problem of prediction of vietnamese student academic performance. International Journal of Advanced Computer Science and Applications, 11(11). https://doi.org/10.14569/ijacsa.2020.0111135
• Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., ... Adam, H. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint, arXiv:1704.04861.
• Hussain, S. (2014). Total path length and number of terminal nodes for decision trees. Procedia Computer Science, 35, 514-521. https://doi.org/10.1016/j.procs.2014.08.132
• Ingsih, K., Kadarningsih, A., & Rijati, N. (2022, February). Job stress, compensation, job dissatisfaction and turnover intention. In Proceedings of the 2nd International Conference on Industry 4.0 and Artificial Intelligence (ICIAI 2021), (pp. 68-72). Atlantis Press. https://doi.org/10.2991/aisr.k.220201.013
• Jaderberg, M., Vedaldi, A., & Zisserman, A. (2014). Speeding up convolutional neural networks with low rank expansions. arXiv preprint, arXiv:1405.3866.
• Ji, H. (2023). Robustness analysis on stock market prediction method. Highlights in Business, Economics and Management, 21, 791-801. https://doi.org/10.54097/hbem.v21i.14763
• Kaharuddin, K., & Sholeha, E. W. (2021). Classification of fish species with image data using k-nearest neighbor. International Journal of Computer and Information System (IJCIS), 2(2), 54-58. https://doi.org/10.29040/ijcis.v2i2.33
• Kanuto, A. E. (2024). Identifying patterns and predicting employee turnover using machine learning approaches. International Journal of Science and Business, 36(1), 20-35. https://doi.org/10.58970/ijsb.2373
• Kim, S. Y., & Fernández, S. (2016). Employee empowerment and turnover intention in the U.S. federal bureaucracy. The American Review of Public Administration, 47(1), 4-22. https://doi.org/10.1177/0275074015583712
• Liao, C. (2023, February). Employee turnover prediction using machine learning models. In Proceedings of the International Conference on Mechatronics Engineering and Artificial Intelligence (MEAI 2022), (227-231), Changsha, China. https://doi.org/10.1117/12.2672733
• Lim, C. S., Malik, E. F., Khaw, K. W., Alnoor, A., Chew, X., Chong, Z. L., … Al Akasheh, M. (2024). Hybrid GA–DeepAutoencoder–KNN Model for employee turnover prediction. Statistics, Optimization & Information Computing, 12(1), 75-90. https://doi.org/10.19139/soic-2310-5070-1799
• Liu, J. E., & An, F. P. (2020). Image classification algorithm based on deep learning‐kernel function. Scientific programming, 2020(1), 1-14. https://doi.org/10.1155/2020/7607612
• Liu, Y., Dou, Y., & Qiao, P. (2020). Beyond top‐n accuracy indicator: A comprehensive evaluation indicator of cnn models in image classification. IET Computer Vision, 14(6), 407-414. https://doi.org/10.1049/iet-cvi.2018.5839
• Marquez, B. Y., Realyvásquez-Vargas, A., Lopez-Esparza, N., & Ramos, C. E. (2023). Application of ordinary least squares regression and neural networks in predicting employee turnover in the industry. Archives of Advanced Engineering Science, 2(1), 30-36. https://doi.org/10.47852/bonviewaaes32021326
• Nagassou, M., Mwangi, R. W., & Nyarige, E. (2023). A hybrid ensemble learning approach utilizing light gradient boosting machine and category boosting model for lifestyle-based prediction of type-ii diabetes mellitus. Journal of Data Analysis and Information Processing, 11(04), 480-511. https://doi.org/10.4236/jdaip.2023.114025
• Natekin, A., & Knoll, A. (2013). Gradient boosting machines, a tutorial. Frontiers in Neurorobotics, 7. https://doi.org/10.3389/fnbot.2013.00021
• Oguine, O. C., & Oguine, M. B. (2021). Comparative analysis and forecasting on the death rate of covid-19 patients in Nigeria using random forest and multinomial bayesian epidemiological models. Journal of Clinical Case Studies, Reviews & Reports, 1-7. https://doi.org/10.47363/jccsr/2021(3)182
• Ogunsanya, M., Isichei, J., & Desai, S. (2023). Grid search hyperparameter tuning in additive manufacturing processes. Manufacturing Letters, 35, 1031-1042.
• Ou, R. (2020). Out-of-core gpu gradient boosting. arXiv preprint, https://doi.org/10.48550/arxiv.2005.09148 Özen, H., & Bal, C. (2019). A study on missing data problem in random forest. Osmangazi̇ Journal of Medicine, 42(1), 103-109. https://doi.org/10.20515/otd.496524
• Pakarinen, O., Karsikas, M., Reito, A., Lainiala, O., Neuvonen, P., & Eskelinen, A. (2022). Prediction model for an early revision for dislocation after primary total hip arthroplasty. Plos One, 17(9), e0274384. https://doi.org/10.1371/journal.pone.0274384
• Pal, S., Pramanik, A., Maiti, J., & Mitra, P. (2021). Deep learning in multi-object detection and tracking: State of the art. Applied Intelligence, 51(9), 6400-6429. https://doi.org/10.1007/s10489-021-02293-7
• Park, D., Kim, S. S., Kwon, H., Shin, D., & Shin, D. (2021). Host-based intrusion detection model using siamese network. IEEE Access, 9, 76614-76623. https://doi.org/10.1109/access.2021.3082160
• Pekel Ozmen, E., & Ozcan, T. (2022). A novel deep learning model based on convolutional neural networks for employee churn prediction. Journal of Forecasting, 41(3), 539-550. https://doi.org/10.1002/for.2827
• Pourkhodabakhsh, N., Mamoudan, M. M., & Bozorgi-Amiri, A. (2022). Effective machine learning, meta-heuristic algorithms and multi-criteria decision making to minimizing human resource turnover. Applied Intelligence, 53(12), 16309-16331. https://doi.org/10.1007/s10489-022-04294-6
• Samašonok, K. (2024). Employee turnover: Causes and retention strategies. Entrepreneurship and Sustainability Issues, 11(3), 134-148. https://doi.org/10.9770/jesi.2024.11.3(9)
• Sarwinda, D., Paradisa, R. H., Bustamam, A., & Anggia, P. (2021). Deep learning in image classification using residual network (ResNet) variants for detection of colorectal cancer. Procedia Computer Science, 179, 423-431. https://doi.org/10.1016/j.procs.2021.01.025
• Sihare, M. (2024). Evaluation of machine learning methods for prediction student performance. International Journal for Research in Applied Science and Engineering Technology, 12(1), 534-544. https://doi.org/10.22214/ijraset.2024.58001
• Siraj, F. M., Ayon, S. T. K., Samad, M. A., Uddin, J., & Choi, K. (2024). Few-shot lightweight squeezenet architecture for induction motor fault diagnosis using limited thermal image dataset. IEEE Access, 12, 50986-50997. https://doi.org/10.1109/access.2024.3385430
• Speer, A. B. (2021). Empirical attrition modelling and discrimination: Balancing validity and group differences. Human Resource Management Journal, 34(1), 1-19. https://doi.org/10.1111/1748-8583.12355
• Srivastava, P. R., & Eachempati, P. (2021). Intelligent employee retention system for attrition rate analysis and churn prediction. Journal of Global Information Management, 29(6), 1-29. https://doi.org/10.4018/jgim.20211101.oa23
• Stamolampros, P., Korfiatis, N., Chalvatzis, K., & Buhalis, D. (2019). Job satisfaction and employee turnover determinants in high contact services: Insights from employees’online reviews. Tourism Management, 75, 130-147. https://doi.org/10.1016/j.tourman.2019.04.030
• Tews, M. J., & Stafford, K. (2020). The impact of abusive supervision and constituent attachment on entry-level employee turnover. Journal of Hospitality; Tourism Research, 44(8), 1318-1334. https://doi.org/10.1177/1096348020947139
• Tong, S., Sun, W., Xu, J., & Li, H. (2024). Robustness analysis and prediction of topological edge states in topological elastic waveguides. Physica Scripta, 99(7), 075402. https://doi.org/10.1088/1402-4896/ad504f
• Viswanadapalli, A. (2021). Efficient data mining model for employees churn prediction and safety measure. Psychology and Education Journal, 58(1), 1962-1982. https://doi.org/10.17762/pae.v58i1.1049
• Wang, L., & Zhao, L. (2022). Digital economy meets artificial intelligence: Forecasting economic conditions based on big data analytics. Mobile Information Systems, 2022, 1-9. https://doi.org/10.1155/2022/7014874
• Wijaya, D., Ds, J. H., Barus, S., Pasaribu, B., Sirbu, L. I., & Dharma, A. (2021). Uplift modeling vs conventional predictive model: A reliable machine learning model to solve employee turnover. International Journal of Artificial Intelligence Research, 5(1). https://doi.org/10.29099/ijair.v4i2.169
• Wu, Y. (2023). Job embeddedness review: Presentation, measurement and development. Advances in Economics, Management and Political Sciences, 47(1), 169-174. https://doi.org/10.54254/2754-1169/47/20230393
• Xue, X., Sun, X., Wang, H., Zhang, H., & Feng, J. (2023). Neural network fusion with fine-grained adaptation learning for turnover prediction. Complex & Intelligent Systems, 9(3), 3355-3366. https://doi.org/10.1007/s40747-022-00931-2
• Zeiler, M. D., & Fergus, R. (2014, September). Visualizing and understanding convolutional networks. In D., Fleet, T., Pajdla, B., Schiele, T. Tuytelaars, (eds) Computer Vision – ECCV 2014. Lecture Notes in Computer Science, vol 8689. Springer, Cham, (818-833), Zurich, Switzerland. https://doi.org/10.1007/978-3-319-10590-1_53
• Zhang, C., Yang, Z., Fang, Z., Li, Y., Li, X., & Zhang, Y. (2024, May). Transformer fault diagnosis method based on gramian angular field and graph convolution network. In Proceedings of the Eighth International Conference on Energy System, Electricity, and Power (ESEP 2023), (1627-1635). SPIE. https://doi.org/10.1117/12.3024388
• Zhang, J. (2024). Neuroscientific prediction model of mouse brain activity patterns. Highlights in Science, Engineering and Technology, 92, 295-301. https://doi.org/10.54097/yecss238
• Zhu, X., Sawhney, R., & Upreti, G. (2016). Determinates of employee voluntary turnover and forecasting in departments: A case study. Studies in Engineering and Technology, 3(1), 64. https://doi.org/10.11114/set.v3i1.1635
• Zia, U. (2024), Employee Attrition Classification Dataset, An In-Depth Synthetic Simulation for Attrition Analysis and Prediction, https://www.kaggle.com/datasets/stealthtechnologies/employee-attrition-dataset/data adresinden erişilmiştir. Erişim Tarihi: 25.07.2024.