GÖÇ ARAŞTIRMALARINDA MAKİNE ÖĞRENMESİ YAKLAŞIMLARI: LİTERATÜR TARAMASINA DAYALI BİR İNCELEME

Öz

Göç, günümüz dünyasında ekonomik, sosyal ve çevresel dinamiklerin etkileşimiyle şekillenen çok boyutlu bir olgu olarak önemini korumaktadır. Geleneksel istatistiksel yaklaşımlar göçün karmaşık doğasını açıklamada sınırlı kalmakta, bu nedenle makine öğrenmesi yöntemleri giderek daha fazla tercih edilmektedir. Bu çalışmada, göç araştırmalarında makine öğrenmesi tabanlı yaklaşımların kullanımı literatür taraması yoluyla incelenmiştir. Değerlendirilen çalışmalar, mülteci entegrasyonunun algoritmik atama modelleriyle geliştirilmesi, ekonomik ve çevresel faktörlerin göç üzerindeki etkilerinin tahmin edilmesi ve düzensiz göç akımlarının öngörülmesi gibi farklı uygulama alanlarını kapsamaktadır. Bulgular, yapay sinir ağları, destek vektör makineleri, karar ağaçları ve ensemble learning yöntemlerinin göçün ekonomik ve toplumsal belirleyicilerini yüksek doğrulukla modellediğini göstermektedir. Bununla birlikte veri yetersizliği, etik kaygılar ve modellerin genellenebilirliği literatürde öne çıkan sınırlılıklar arasındadır. Sonuç olarak, makine öğrenmesi göç araştırmalarında güçlü bir analitik araç olarak öne çıkmakta ve göç politikalarının veri odaklı biçimde tasarlanmasına katkı sağlamaktadır. Bu çalışma, mevcut literatürü sistematik biçimde değerlendirerek hem akademik araştırmalara hem de politika yapıcılara yol gösterici bir çerçeve sunmaktadır.

Anahtar Kelimeler

• Makine Öğrenmesi
• Göç
• Ekonomik Etkiler

MACHINE LEARNING APPROACHES IN MIGRATION RESEARCH: A REVIEW BASED ON LITERATURE SCREENING

Öz

Migration remains a multidimensional phenomenon shaped by the interaction of economic, social, and environmental dynamics in today's world. Traditional statistical approaches have limitations in explaining the complex nature of migration, leading to an increasing preference for machine learning methods. This study examines the use of machine learning-based approaches in migration research through a literature review. The evaluated studies cover different application areas, such as improving refugee integration with algorithmic assignment models, predicting the effects of economic and environmental factors on migration, and forecasting irregular migration flows. The findings show that artificial neural networks, support vector machines, decision trees, and ensemble learning methods model the economic and social determinants of migration with high accuracy. However, data insufficiency, ethical concerns, and the generalizability of models are among the limitations highlighted in the literature. In conclusion, machine learning stands out as a powerful analytical tool in migration research and contributes to the data-driven design of migration policies. This study provides a guiding framework for both academic research and policymakers by systematically reviewing the existing literature.

Anahtar Kelimeler

• Machine Learning
• Migration
• Economic Impacts

Kaynakça

1. Anuar, A., Hussain, N., Masrom, S., Mohd, T., Ahmad, S., & Ahmad, N. (2023). Reverse migration factor in machine learning models. *International Journal of Academic Research in Business and Social Sciences, 13*(2), 16282. [https://doi.org/10.6007/ijarbss/v13-i2/16282](https://doi.org/10.6007/ijarbss/v13-i2/16282)
2. Aoga, J., Bae, J., Veljanoska, S., Nijssen, S., & Schaus, P. (2020). Impact of weather factors on migration intention using machine learning algorithms. *Operations Research Forum, 5,* 1–37. [https://doi.org/10.1007/s43069-023-00271-y](https://doi.org/10.1007/s43069-023-00271-y)
3. Aydemir, B., Aydın, H., Çetinkaya, A., & Polat, D. (2022). Predicting the income groups and number of immigrants by using machine learning (ML). *International Journal of Multidisciplinary Studies and Innovative Technologies, 6*(2), 162–168. [https://doi.org/10.36287/ijmsit.6.2.162](https://doi.org/10.36287/ijmsit.6.2.162)
4. Bansak, K., Ferwerda, J., Hainmueller, J., Dillon, A., Hangartner, D., Lawrence, D., & Weinstein, J. (2018). Improving refugee integration through data-driven algorithmic assignment. *Science, 359*(6373), 325–329. [https://doi.org/10.1126/science.aao4408](https://doi.org/10.1126/science.aao4408)
5. Best, K., Gilligan, J., Baroud, H., Carrico, A., Donato, K., & Mallick, B. (2022). Applying machine learning to social datasets: A study of migration in southwestern Bangladesh using random forests. *Regional Environmental Change, 22*(112). [https://doi.org/10.1007/s10113-022-01915-1](https://doi.org/10.1007/s10113-022-01915-1)
6. Carammia, M., Iacus, S. M., & Wilkin, T. (2020). Forecasting asylum-related migration flows with machine learning and data at scale. *Scientific Reports, 12*(1), 1–12. [https://doi.org/10.1038/s41598-022-05241-8](https://doi.org/10.1038/s41598-022-05241-8)
7. Czaika, M. (2015). Migration and economic prospects. *Journal of Ethnic and Migration Studies, 41*(1), 58–82. [https://doi.org/10.1080/1369183X.2014.924848](https://doi.org/10.1080/1369183X.2014.924848)
8. De Bruin, S., Hoch, J., De Bruijn, J., Hermans, K., Maharjan, A., Kummu, M., & Van Vliet, J. (2024). Scenario projections of South Asian migration patterns amidst environmental and socioeconomic change. *Global Environmental Change, 85,* 102920. [https://doi.org/10.1016/j.gloenvcha.2024.102920](https://doi.org/10.1016/j.gloenvcha.2024.102920)

9. Devillanova, C., Fasani, F., & Frattini, T. (2018). Employment of undocumented immigrants and the prospect of legal status: Evidence from an amnesty program. *ILR Review, 71*(4), 853–881. [https://doi.org/10.1177/0019793917743246](https://doi.org/10.1177/0019793917743246)
10. Dziadula, E., O’Hare, J., Colglazier, C., Clay, M., & Brenner, P. (2023). Modeling economic migration on a global scale. *Journal of Computational Social Science, 6*(4), 1125–1145. [https://doi.org/10.1007/s42001-023-00226-7](https://doi.org/10.1007/s42001-023-00226-7)
11. Ertürkmen, G., & Öter, A. (2025). Makina Öğrenmesi Yoluyla İşsizlik Oranlarının Tahmini: Türkiye İçin Bir Uygulama. *İnsan ve Toplum Bilimleri Araştırmaları Dergisi, 14*(2), 869–886. [https://doi.org/10.15869/itobiad.1629420](https://doi.org/10.15869/itobiad.1629420)
12. Freund, D., Lykouris, T., Paulson, E., Sturt, B., & Weng, W. (2023). Group fairness in dynamic refugee assignment. In *Proceedings of the 24th ACM Conference on Economics and Computation* (pp. 896–918). ACM. [https://doi.org/10.1145/3580507.3597758](https://doi.org/10.1145/3580507.3597758)
13. Hameed Ashour, M., & Al-Dahhan, I. (2024). Forecasting net migration rate using support vector machine. In *2024 International Conference on Electrical, Computer and Energy Technologies (ICECET)* (pp. 1–4). IEEE. [https://doi.org/10.1109/ICECET61485.2024.10698383](https://doi.org/10.1109/ICECET61485.2024.10698383)
14. Haris, R., Barhamgi, M., Nhlabatsi, A., & Khan, K. (2024). Optimizing pre-copy live virtual machine migration in cloud computing using machine learning-based prediction model. *Computing, 106*(11), 3031–3062. [https://doi.org/10.1007/s00607-024-01318-6](https://doi.org/10.1007/s00607-024-01318-6)
15. Horvath, T., & Huber, P. (2018). Regional ethnic diversity and the employment prospects of immigrants. *Regional Studies, 53*(2), 272–282. [https://doi.org/10.1080/00343404.2018.1462479](https://doi.org/10.1080/00343404.2018.1462479)
16. Hussain, N. (2021). Machine learning of the reverse migration models for population prediction: A review. *Turkish Journal of Computer and Mathematics Education, 12*(5), 1830–1838. [https://doi.org/10.17762/turcomat.v12i5.2197](https://doi.org/10.17762/turcomat.v12i5.2197)
17. Islam, M., Rahim, M., Podder, N., Hossain, M., & Hossain, M. (2024). Prediction of irregular Bangladesh-EU migration trends using machine learning techniques. In *2024 3rd International Conference on Advancement in Electrical and Electronic Engineering (ICAEEE)* (pp. 1–6). IEEE. [https://doi.org/10.1109/ICAEEE62219.2024.10561697](https://doi.org/10.1109/ICAEEE62219.2024.10561697)
18. Jasny, B. (2018). Data-driven refugee assignment. *Science, 359*(6373), 285. [https://doi.org/10.1126/science.359.6373.285-a](https://doi.org/10.1126/science.359.6373.285-a)
19. Khangahi, F., & Kiani, F. (2021). Social mobilization and migration predictions by machine learning methods: A study case on Lake Urmia. *International Journal of Innovative Technology and Exploring Engineering, 10*(4), 123–127. [https://doi.org/10.35940/ijitee.F8833.0410621](https://doi.org/10.35940/ijitee.F8833.0410621)
20. Kiossou, H., Schenk, Y., Docquier, F., Houndji, V., Nijssen, S., & Schaus, P. (2020). Using an interpretable machine learning approach to study the drivers of international migration. *arXiv preprint* arXiv:2006.03560. [https://arxiv.org/abs/2006.03560](https://arxiv.org/abs/2006.03560)
21. Kovalchuk, O., Berezka, K., Babala, L., Ivanytskyy, R., Karpyshyn, N., & Zhuk, N. (2024). Modeling country economic security: A machine learning approach. In *2024 14th International Conference on Advanced Computer Information Technologies (ACIT)* (pp. 370–375). IEEE. [https://doi.org/10.1109/ACIT62333.2024.10712462](https://doi.org/10.1109/ACIT62333.2024.10712462)
22. Kwiliński, A., Lyulyov, O., Pimonenko, T., Dźwigoł, H., Abazov, R., & Pudryk, D. (2022). International migration drivers: Economic, environmental, social, and political effects. *Sustainability, 14*(11), 6413. [https://doi.org/10.3390/su14116413](https://doi.org/10.3390/su14116413)
23. Lu, Y. (2022). Detecting imperfect substitution between comparably skilled immigrants and natives: A machine learning approach. *International Migration Review, 57*(4), 1184–1215. [https://doi.org/10.1177/01979183221126467](https://doi.org/10.1177/01979183221126467)
24. Maj, J., Ruszczak, B., & Kubiciel-Lodzińska, S. (2024). Towards algorithm-assisted career management – The challenge for new immigration countries: Predicting the migrant’s work trajectory using ensemble learning. *Central European Business Review, 13*(1), 87–101. [https://doi.org/10.18267/j.cebr.365](https://doi.org/10.18267/j.cebr.365)
25. Morgenstern, S., & Strijbis, O. (2024). Forecasting migration movements using prediction markets. *Comparative Migration Studies, 12*(1), 28. [https://doi.org/10.1186/s40878-024-00404-0](https://doi.org/10.1186/s40878-024-00404-0)
26. Pyshnograev, I., & Vasiltsova, Y. (2021). Modeling the impact of socio-economic crises on migration process. *Problems of Systemic Approach in the Economy, 2021*(6), 128–134. [https://doi.org/10.32782/2520-2200/2021-6-14](https://doi.org/10.32782/2520-2200/2021-6-14)
27. Robinson, C., & Dilkina, B. (2017). A machine learning approach to modeling human migration. In *Proceedings of the 1st ACM SIGCAS Conference on Computing and Sustainable Societies* (pp. 1–6). ACM. [https://doi.org/10.1145/3209811.3209868](https://doi.org/10.1145/3209811.3209868)
28. Saxena, A., Asbe, C., & Vashishth, T. (2023). Leveraging a novel machine learning approach to forecast income and immigration dynamics. *Multidisciplinary Science Journal, 5*(2), 15–24. [https://doi.org/10.31893/multiscience.2023ss0202](https://doi.org/10.31893/multiscience.2023ss0202)
29. Stoica, R., Vilău, R., Voicu, D., & Grzelak, M. (2024). Application of machine learning methods to analyze customer migration risk in terms of corporate financial security. *Systemy Logistyczne Wojsk, 60*(1), 63–78. [https://doi.org/10.37055/slw/186379](https://doi.org/10.37055/slw/186379)
30. Tarasyev, A., Agarkov, G., & Hosseini, S. (2018). Machine learning in labor migration prediction. In *AIP Conference Proceedings* (Vol. 1978, p. 440004). AIP Publishing. [https://doi.org/10.1063/1.5044033](https://doi.org/10.1063/1.5044033)
31. Tiwari, R. (2023). The impact of AI and machine learning on job displacement and employment opportunities. *International Journal of Scientific Research in Engineering and Management, 7*(5), 1–7. [https://doi.org/10.55041/ijsrem17506](https://doi.org/10.55041/ijsrem17506)
32. Yapamanu, G., Thugutla, K., Undela, V., & Vidhya, M. (2025). Predict migration using machine learning. *International Journal on Science and Technology, 16*(1), 2612. [https://doi.org/10.71097/ijsat.v16.i1.2612](https://doi.org/10.71097/ijsat.v16.i1.2612)