Saatlik Asgari Ücrete Yönelik Bireysel Tutumların Makine ve Derin Öğrenme ile Sınıflandırılması

Yıl 2026, Cilt: 28 Sayı: 1 , 81 - 124 , 20.04.2026

Emre Ünal , Yunus Emre Gür , Muhammed Mesut Turan

https://doi.org/10.26745/ahbvuibfd.1764260

https://izlik.org/JA55GY94ZZ

Öz

Bu çalışma, Türkiye’de saatlik asgari ücret sistemine geçişin çalışanlar nezdindeki kabul düzeyini anlamak amacıyla, birey temelli tutumların makine öğrenmesi ve derin öğrenme algoritmalarıyla sınıflandırılmasını hedeflemektedir. Veri seti, Elazığ ilinde aktif olarak çalışan 343 bireyden yapılandırılmış anket formu yoluyla elde edilmiştir. Anket kapsamında sosyodemografik, psikolojik ve davranışsal özelliklere dair çok sayıda değişken toplanmış; katılımcıların saatlik asgari ücret sistemine ilişkin “evet” ya da “hayır” yönündeki tutumları hedef değişken olarak belirlenmiştir. Bu tutumlar, Lojistik Regresyon, Rastgele Orman, XGBoost, CatBoost, LogisticGAM ve TabNet modelleriyle sınıflandırılmış; hiperparametre optimizasyonları GridSearchCV ve Optuna yöntemleriyle gerçekleştirilmiştir. Test verisinde en yüksek doğruluk (%94) ve AUC (%99.7) performansı TabNet modeli tarafından elde edilmiştir. Ayrıca, LogisticGAM modeli doğrusal olmayan yapılar üzerindeki başarısıyla dikkat çekmiştir (%84 doğruluk). En iyi sınıflandırma sonucunu veren TabNet modelinin sınıf bazlı öznitelik katkı analizleri ile yorumlanarak, çalışanların ücret algısı, iş tatmini, performansa dayalı ücretlendirme görüşü ve esnek çalışmaya yönelik eğilimlerinin tutumları üzerindeki etkileri açıklanmıştır. Çalışma, Türkiye’de saatlik asgari ücret bağlamında yapay zekâ temelli ilk birey düzeyli sınıflandırma uygulaması olma niteliği taşımakta; sosyal politika analizine açıklanabilir yapay zekâ modelleri aracılığıyla özgün bir metodolojik katkı sunmaktadır.

Anahtar Kelimeler

Saatlik Asgari Ücret , Bireysel Tutumlar , Makine Öğrenmesi , Derin Öğrenme , Sosyal Politika

The Classification of Individual Attitudes Toward the Hourly Minimum Wage Using Machine and Deep Learning

https://izlik.org/JA55GY94ZZ

Öz

This study aims to understand the level of acceptance of the transition to an hourly minimum wage system in Turkey among workers by classifying individual-based attitudes using machine learning and deep learning algorithms. The data set was obtained through structured survey forms from 343 individuals actively working in Elazığ province. The survey collected numerous variables related to sociodemographic, psychological, and behavioral characteristics; participants' attitudes toward the hourly minimum wage system, categorized as “yes” or “no,” were designated as the target variable. These attitudes were classified using Logistic Regression, Random Forest, XGBoost, CatBoost, LogisticGAM, and TabNet models; hyperparameter optimizations were performed using GridSearchCV and Optuna methods. The highest accuracy (94%) and AUC (99.7%) performance in the test data was achieved by the TabNet model. Additionally, the LogisticGAM model stood out for its success on non-linear structures (84% accuracy). The class-based feature contribution analysis of the TabNet model, which yielded the best classification result, was interpreted to explain the effects of employees' perceptions of wages, job satisfaction, views on performance-based pay, and tendencies toward flexible work on their attitudes. The study represents the first individual-level classification application based on artificial intelligence in the context of hourly minimum wage in Turkey, offering a unique methodological contribution to social policy analysis through explainable artificial intelligence models.

Anahtar Kelimeler

Hourly Minimum Wage , Individual Attitudes , Machine Learning , Deep Learning , Social Policy

Kaynakça

• Adekoya, O. D., Mordi, C., Ajonbadi, H. A., & Chen, W. (2025). Implications of algorithmic management on careers and employment relationships in the gig economy–a developing country perspective. Information Technology & People, 38(2), 686-713. https://doi.org/10.1108/ITP-01-2023-0064
• Bansal, A., Mukherjee, S., & Prayag, G. (2025). From crisis to care: Redesigning work and jobs for employee well-being in hospitality and tourism. Tourism and Hospitality Research, 14673584251321038. https://doi.org/10.1177/14673584251321
• Bhorat, H., Kanbur, R., & Mayet, N. (2013). The impact of sectoral minimum wage laws on employment, wages, and hours of work in South Africa. IZA Journal of Labor & Development, 2(1), 1.
• Caliendo, M., Wittbrodt, L., & Schröder, C. (2019). The causal effects of the minimum wage introduction in Germany–an overview. German Economic Review, 20(3), 257-292. https://doi.org/10.1111/geer.12191
• Couch, K. A., & Wittenburg, D. C. (2001). The response of hours of work to increases in the minimum wage. Southern Economic Journal, 68(1), 171-177. https://doi.org/10.1002/j.2325-8012.2001.tb00406.x
• Coviello, D., Deserranno, E., & Persico, N. (2022). Minimum wage and individual worker productivity: Evidence from a large US retailer. Journal of Political Economy, 130(9), 2315-2360. https://doi.org/10.1086/720397
• Çelik, A., & Koç, A. (2024). Asgari ücret ve ekonomik büyüme hızının emek ve sermaye gelirlerine etkisi: OECD ülkeleri için sistem GMM yaklaşımı. Bulletin of Economic Theory and Analysis, 9(1), 145-170.
• Doh, T., Kim, K., Kim, S., Lee, H., & Song, K. (2025). The economic effects of a rapid increase in the minimum wage: Evidence from South Korea experiments. Federal Reserve Bank of Kansas City Working Paper, (22-13). http://dx.doi.org/10.2139/ssrn.4292238
• Gök, M. (2017). Makine öğrenmesi yöntemleri ile akademik başarinin tahmin edilmesi. Gazi University Journal of Science Part C: Design and Technology, 5(3), 139-148.
• Gür, Y. E., & Ayden, C. (2025). Cnn Tabanlı Derin Öğrenme ve Makine Öğrenmesi Tekniklerinin Entegrasyonu: İşten Ayrılma Tahminlerinde Yeni Bir Metodoloji. Uluslararası Yönetim İktisat ve İşletme Dergisi, 21(1), 161-198. https://doi.org/10.17130/ijmeb.1529822
• Hanley, C., & Branch, E. H. (2025). Precarious Jobs, Precarious Lives? A Cohort Analysis of Trends in Hourly Employment. Social Currents, 12(2), 129-156. https://doi.org/10.1177/23294965251324507
• Hayes, A. S., & Miletzky, Y. (2024). Rethinking economic socialization: the intersection of culture, gender and economic life in a religious enclave. Socio-Economic Review, mwae063. https://doi.org/10.1093/ser/mwae063
• He, Y. B., Sheng, K. M., Du, M. L., Jiang, G. C., Dong, T. F., Guo, L., & Xu, B. T. (2025). An interpretable deep learning framework using FCT-SMOTE and BO-TabNet algorithms for reservoir water sensitivity damage prediction. Scientific Reports, 15, 18655. https://doi.org/10.1038/s41598-025-99659-5
• Henshaw, B., Mishra, B. K., Sayers, W., & Pervez, Z. (2025). Unveiling the Impact of Socioeconomic and Demographic Factors on Graduate Salaries: A Machine Learning Explanatory Analytical Approach Using Higher Education Statistical Agency Data. Analytics, 4(1), 10. https://doi.org/10.3390/analytics4010010
• Hicks, J.R. (1963). The theory of wages. Palgrave Macmillan, Toronto.
• Imani, M., Beikmohammadi, A., & Arabnia, H. R. (2025). Comprehensive Analysis of Random Forest and XGBoost Performance with SMOTE, ADASYN, and GNUS Under Varying Imbalance Levels. Technologies, 13(3), 88. https://doi.org/10.3390/technologies13030088
• İnan, M., Demir, R., & Demir, M. (2025). Sosyal Politika Aracı Olarak Asgari Ücret: Türkiye Üzerine Bir İnceleme. Akademik Araştırmalar ve Çalışmalar Dergisi (AKAD), 17(32), 72-95. https://doi.org/10.20990/kilisiibfakademik.1654655
• Islam, M. M., Liu, J., Chakraborty, R., & Das, S. (2025). Evaluating crash risk factors of farm equipment vehicles on county and non-county roads using interpretable tabular deep learning (TabNet). Accident Analysis & Prevention, 217, 108048. https://doi.org/10.1016/j.aap.2025.108048
• Jia, P. (2014). Employment and working hour effects of minimum wage increase: Evidence from China. China & World Economy, 22(2), 61-80. https://doi.org/10.1111/j.1749-124X.2014.12062.x
• Kamphorst, J. (2025). The Left Misunderstood: How Voters' Perceptions of What Matters to the Left Benefit the Right, May 01, http://dx.doi.org/10.2139/ssrn.5238518
• Kannan, M., Umamaheswari, D., Manimekala, B., Mary, I. P. S., Savitha, P. M., & Rozario, J. (2025). An enhancement of machine learning model performance in disease prediction with synthetic data generation. Scientific Reports, 15, 33482. https://doi.org/10.1038/s41598-025-15019-3
• Kebebe, F. (2025). The influence of Variable Payment Structures on Employee Motivation, Job Satisfaction, and Performance at Ethio telecom, Doctoral dissertation, St. Mary’s University, Addis Abeba, Ethiopia.
• Khanphet, J., & Phayaphrom, B. (2024), The Effectiveness of Different Performance-Based Pay Models in the Thai Jewelry Industry. International Journal of Latest Research in Humanities and Social Science (IJLRHSS), 7(12), 58-73.
• Khoso, F. H., Baseer, A., ul Haq, M. I., Hassan, S., & Afzal, I. (2025). Analysis of Labor Policies and Their Impact on Employment and Economic Growth. Review Journal of Social Psychology & Social Works, 3(2), 374-381. https://doi.org/10.71145/rjsp.v3i2.200
• Kim, D., Chung, C. J., & Eom, K. (2022). Measuring Online Public Opinion for Decision Making: Application of Deep Learning on Political Context. Sustainability, 14(7), 4113. https://doi.org/10.3390/su14074113
• Kirkizh, N., Ulloa, R., Stier, S., & Pfeffer, J. (2024). Predicting political attitudes from web tracking data: a machine learning approach. Journal of Information Technology & Politics, 21(4), 564-577. https://doi.org/10.1080/19331681.2024.2316679
• Kotola, V. K. (2024). Mental Health in the Workplace: A cost-benefit analysis. Metropolia University of Applied Sciences, Bachelor of Business Administration, European Business Administration, Bachelor’s Thesis.
• Krasnyak, O., & Amons, S. (2021). THEORETICAL FUNDAMENTALS OF LABOR MOTIVATION AND ITS STIMULATION AT DOMESTIC ENTERPRISES. In Colloquium-journal (No. 15-5, pp. 41-47). Голопристанський міськрайонний центр зайнятості= Голопристанский районный центр занятости.
• Ku, H. (2022). Does minimum wage increase labor productivity? Evidence from piece rate workers. Journal of Labor Economics, 40(2), 325-359. https://doi.org/10.1086/716347
• Kugler, P. (2022). Using Machine Learning Methods to study research questions in health, labor and family economics, Doctoral dissertation, Universität Tübingen.
• Liu, K., Prommawin, B., & Schroyen, F. (2024). Health insurance, agricultural production and investments. Journal of Health Economics, 97, 102918. https://doi.org/10.1016/j.jhealeco.2024.102918
• Mashunye, N., & Silwimba, P. (2025). Analyzing the effect of Minimum wage on Employment situation: A case study of small-scale businesses in Lusaka district. International Journal of Advanced Multidisciplinary Research and Studies, 5(2), 256-263. https://doi.org/10.62225/2583049X.2025.5.2.3836
• Mastracci, S. H., & Persky, J. J. (2008). Effects of state minimum wage increases on employment, hours, and earnings of low-wage workers in Illinois. Journal of regional analysis and policy, 38(3), 268-278. https://doi.org/10.22004/ag.econ.133004
• Munmun, Z. S., Akter, S., & Parvez, C. R. (2025). Machine Learning-Based Classification of Coronary Heart Disease: A Comparative Analysis of Logistic Regression, Random Forest, and Support Vector Machine Models. Open Access Library Journal, 12(3), 1-12. https://doi.org/10.4236/oalib.1113054
• Özdemir, O., Karakütük, F., & Kaya Karakütük, A. (2025). Veri Madenciliğinde Karar Ağaçları İndükleyicilerinin Likert Ölçekli Verilerde Sınıflandırma Performansı. Süleyman Demirel Üniversitesi Fen Bilimleri Enstitüsü Dergisi, 29(1), 72-83. https://doi.org/10.19113/sdufenbed.1596624
• Rabbani, S. B., Medri, I. V., & Samad, M. D. (2025). Attention versus contrastive learning of tabular data: a data-centric benchmarking. International Journal of Data Science and Analytics, 20, 3069-3091. https://doi.org/10.1007/s41060-024-00681-z
• Samart, W., & Kilenthong, W. T. (2024). Minimum Wage Effects on Labor Market Outcomes: Evidence from Thailand. Thailand and The World Economy, 42(1), 1-21.
• Skular, A., Jin, L., Overton, J. A., & Saez, I. (2025). Neuromodulation of risk preferences encoded in human orbitofrontal cortex activity. bioRxiv, 2025-05. https://doi.org/10.1101/2025.05.06.650317
• Sun, J., Liao, R., Shalaginov, M. Y., & Zeng, T. H. (2022, December). A Machine-Learning Approach for Predicting Depression Through Demographic and Socioeconomic Features. In 2022 IEEE International Conference on Bioinformatics and Biomedicine, pp. 2203-2207. https://doi.org/10.1109/BIBM55620.2022.9994921
• Tauil, Y. B., dos Santos, B. S., & Lima, R. H. P. (2024). Machine learning techniques in classifying satisfaction with the economy of Latin American Citizens. Observatorio De La Economía Latinoamericana, 22(5), e4912-e4912. https://doi.org/10.55905/oelv22n5-199
• Theodorakopoulos, L., Theodoropoulou, A., Tsimakis, A., & Halkiopoulos, C. (2025). Big Data-Driven Distributed Machine Learning for Scalable Credit Card Fraud Detection Using PySpark, XGBoost, and CatBoost. Electronics, 14(9), 1754. https://doi.org/10.3390/electronics14091754
• Trivelli, R., Smacchia, M., Cipriano, M., & Za, S. (2025). Fluid work practices and AI: a computational literature review. Personnel Review. Vol. ahead-of-print No. ahead-of-print. https://doi.org/10.1108/PR-05-2024-0528
• Turgut, M. (2025). Türkiye için adil bir ücret politikasi modeli: Bölgesel asgari ücret. Uluslararası Finansal Ekonomi ve Bankacılık Uygulamaları Dergisi, 6(1), 1-24. https://doi.org/10.57085/ufebud.1598159
• Ünal, E. (2016) A comparative analysis of export growth in Turkey and China through macroeconomic and institutional factors, Evolutionary Institutional Economic Review, 131: 57–91. https://doi.org/10.1007/s40844-016-0036-3
• Ünal, E. (2018) An institutional approach and input-output analysis for explaining the transformation of Turkish economy, Journal of Economic Structure, 73:1–38. https://doi.org/10.1186/s40008-017-0101-z
• Ukponahiusi, O., & Ahuru, R. R. (2024). A Systematic Review of the Impact of Incentives on Job Performance Among Healthcare Workers in Africa. African Journal of Social and Behavioural Sciences, 14(8), 4709-4727.
• Uzun Arslan, R., Şenyer Yapıcı, İ., & Alkan, F. (2025). Bireylerin Çevresel Tutumlarını Tahminde Makine Öğrenmesi: ANOVA ve Ki-Kare Temelli Özellik Seçimi ile Algoritma Performanslarının Karşılaştırılması. EMO Bilimsel Dergi, 15(2), 61-69.
• Wang, H., Maruejols, L., & Yu, X. (2021). Predicting energy poverty with combinations of remote-sensing and socioeconomic survey data in India: evidence from machine learning. Energy Economics, 102, 105510. https://doi.org/10.1016/j.eneco.2021.105510
• Weber, P., Weber, N., Goesele, M., & Kabst, R. (2018). Prospect for knowledge in survey data: an artificial neural network sensitivity analysis. Social Science Computer Review, 36(5), 575-590. https://doi.org/10.1177/0894439317725
• Wimmer, B. S. (2000). The minimum wage and productivity differentials. Journal of Labor Research, 21(4), 649-668. https://doi.org/10.1007/s12122-000-1038-8
• Wheatley, M. C. (2024). Redefining Work: The GigEconomy’s Impact on Work and Life. Premier Journal of Business and Management, 1:100005. https://doi.org/10.70389/PJBM.100005
• Wiens, M., Verone‐Boyle, A., Henscheid, N., Podichetty, J. T., & Burton, J. (2025). A tutorial and use case example of the eXtreme gradient boosting (XGBoost) artificial intelligence algorithm for drug development applications. Clinical and Translational Science, 18(3), e70172. https://doi.org/10.1111/cts.70172
• Wong, S. A. (2019). Minimum wage impacts on wages and hours worked of low-income workers in Ecuador. World Development, 116, 77-99. https://doi.org/10.1016/j.worlddev.2018.12.004
• Yelboğa, A. (2007). Bireysel demografik değişkenlerin iş doyumu ile ilişkisinin finans sektöründe incelenmesi. Çağ Üniversitesi Sosyal Bilimler Dergisi, 4(2), 1-18.
• Zavodny, M. (2000). The effect of the minimum wage on employment and hours. Labour Economics, 7(6), 729-750. https://doi.org/10.1016/S0927-5371(00)00021-X
• Zhang, T., Guo, H., Song, L., Yuan, H., Sui, H., & Li, B. (2025). Evaluating the importance of vertical environmental variables for albacore fishing grounds in tropical Atlantic Ocean using machine learning and Shapley additive explanations (SHAP) approach. Fisheries Oceanography, 34(1), e12701. https://doi.org/10.1111/fog.12701
• Zhao, Y., Wang, J., Tan, X., Wen, L., Gao, Q., & Wang, W. (2025). Privacy-Preserving and Interpretable Grade Prediction: A Differential Privacy Integrated TabNet Framework. Electronics, 14(12), 2328. https://doi.org/10.3390/electronics14122328