Türkiye'ye Yönelik Yabancı Turizm Talebinin Öngörülmesi: Reel Efektif Döviz Kuru, Mevsimsellik ve Makine Öğrenmesi Modelleri (Forecasting Foreign Tourism Demand for Türkiye: Real Effective Exchange Rate, Seasonality, and Machine Learning Models)
DOI:
https://doi.org/10.63556/jotags.2026.1930Keywords:
Tourism demand, Real effective exchange rate, Machine learning, SeasonalityAbstract
This study aims to forecast foreign tourism demand for Türkiye using machine learning methods and to assess the role of the real effective exchange rate and seasonality in the forecasting process. Monthly data covering the period 2005:M1–2025:M12 are employed. The number of foreign visitors is used as the dependent variable, while the real effective exchange rate, unemployment, inflation, economic growth, and population growth are included as explanatory variables. Monthly seasonality is represented through sine and cosine transformations. Random Forest, Gradient Boosting, and Multilayer Perceptron models are compared in forecasting tourism demand. For the 2023:M1–2025:M12 test period, Gradient Boosting produces the lowest forecast errors, with an MAE of 675,351.02 and an RMSE of 798,635.93. The findings indicate that foreign tourism demand for Türkiye exhibits a strong seasonal pattern and can be effectively forecast using machine learning techniques. For the forward-looking analysis, the Gradient Boosting model is employed under baseline, favorable, and unfavorable real effective exchange rate scenarios. Under the baseline scenario, annual foreign visitor arrivals are projected to remain at approximately 53.6–54.1 million during 2027–2030. Overall, the results highlight the importance of jointly considering macroeconomic conditions, price competitiveness, and seasonal dynamics in forecasting international tourism demand.
References
Adil, M., Wu, J.-Z., Chakrabortty, R. K., Alahmadi, A., Ansari, M. F., & Ryan, M. J. (2021). Attention-based STL-BiLSTM network to forecast tourist arrival. Processes, 9(10), 1759. https://doi.org/10.3390/pr9101759
Agan Celik, B., Yulek, M., & Çelik, S. (2026). Machine learning assessment of drivers of tourist arrivals in Istanbul: Evidence from economic, climatic and behavioral indicators. Journal of Hospitality and Tourism Technology. Advance online publication. https://doi.org/10.1108/JHTT-08-2025-0686
Apaydın, Ş. (2019). Türkiye’de işsizliğin kaynakları: Bir yapısal vektör hata düzeltme modeli. MANAS Sosyal Araştırmalar Dergisi, 8(1), 1002–1016. https://doi.org/10.33206/mjss.464857
Bilek, G. (2025). Modeling tourism demand in Turkey (2008–2024): Time-series approaches for sustainable growth. Sustainability, 17(4), 1396. https://doi.org/10.3390/su17041396
Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324
Dimitriadou, A., Gogas, P., & Papadimitriou, T. (2025). Tourism and uncertainty: A machine learning approach. Current Issues in Tourism, 28(14), 2278–2298. https://doi.org/10.1080/13683500.2024.2370380
Ertürkmen, G., & Öter, A. (2025). Makina öğrenmesi yoluyla işsizlik oranlarının tahmini: Türkiye için bir uygulama. İnsan ve Toplum Bilimleri Araştırmaları Dergisi, 14(2), 869–886. https://doi.org/10.15869/itobiad.1629420
Fotiadis, A., Polyzos, S., & Huan, T. T. C. (2021). The good, the bad and the ugly on COVID-19 tourism recovery. Annals of Tourism Research, 87, 103117. https://doi.org/10.1016/j.annals.2020.103117
Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. Annals of Statistics, 29(5), 1189–1232. https://doi.org/10.1214/aos/1013203451
Grau-Escolano, J., Anton Clavé, S., & Borràs, J. (2026). Daily tourism demand forecasting via card transactions: A multi-source, interpretable framework for diverse destinations and markets. Information Technology & Tourism, 28. https://doi.org/10.1007/s40558-025-00350-2
Haykin, S. (2009). Neural networks and learning machines (3rd ed.). Pearson Education.
He, M., & Qian, X. (2026). Forecasting tourist arrivals using STL-XGBoost method. Tourism Economics, 32(2), 408–436. https://doi.org/10.1177/13548166241313411
Jiao, E., & Chen, J. (2019). Tourism forecasting: A review of methodological developments over the last decade. Tourism Economics, 25(3), 469–492. https://doi.org/10.1177/1354816618812588
Kara Gülay, B. (2024). Modeling and forecasting of tourism income: The case of Turkey. Erciyes Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, 69, 251–257. https://doi.org/10.18070/erciyesiibd.1581119
Kurtulay, Z., & Kızılırmak, İ. (2024). Forecasting Türkiye's international tourism demand. Journal of Global Tourism and Technology Research, 5(1), 12–26. https://doi.org/10.54493/jgttr.1408566
Law, R., Li, G., Fong, D., & Han, X. (2019). Tourism demand forecasting: A deep learning approach. Annals of Tourism Research, 75, 410–423. https://doi.org/10.1016/j.annals.2019.01.014
Li, X., Li, H., Pan, B., & Law, R. (2021). Machine learning in internet search query selection for tourism forecasting. Journal of Travel Research, 60(6), 1213–1231. https://doi.org/10.1177/0047287520934871
Makoni, T., Mazuruse, G., & Nyagadza, B. (2023). International tourist arrivals modelling and forecasting: A case of Zimbabwe. Sustainable Technology and Entrepreneurship, 2(1), 100027. https://doi.org/10.1016/j.stae.2022.100027
Mishra, R. K., Urolagin, S., Jothi, J. A., Nawaz, N., & Ramkissoon, H. (2021). Machine learning based forecasting systems for worldwide international tourists arrival. International Journal of Advanced Computer Science and Applications, 12(11). https://doi.org/10.14569/IJACSA.2021.0121107
Sevim, U., & Oğan, E. (2020). Reel döviz kuru ile turizm sektörü arasındaki nedenselliğin değerlendirilmesi: Türkiye örneği. Gümüşhane Üniversitesi Sosyal Bilimler Dergisi, 11(3), 858–869. https://doi.org/10.36362/gumus.697246
Sutisna, E., Dafitri, R., & Daryani, D. (2026). Forecasting foreign tourist arrivals in Indonesia using Google Trends Index as exogenous variable: A comparative study of SARIMAX and LSTM models. Journal of Applied Informatics and Computing, 10(2). https://doi.org/10.30871/jaic.v10i2.12384
Sürekçi Yamaçlı, D. (2023). Modelling the exchange rates in Türkiye employing machine learning methods. Cognizance Journal, 3(6). https://doi.org/10.47760/cognizance.2023.v03i06.004
Ünlüönen, K., & Gündüz, S. (2025). Türkiye’de reel efektif döviz kurunun yurt içi turizm talebine etkisi. Ankara Hacı Bayram Veli Üniversitesi Turizm Fakültesi Dergisi, 28(2), 194–210. https://doi.org/10.55931/ahbvtfd.1831221
Wang, H., & Liu, W. (2022). Forecasting tourism demand by a novel multi-factors fusion approach. IEEE Access, 10, 125972–125991. https://doi.org/10.1109/ACCESS.2022.3225958
Yağmur, İ. (2026). Investigating the validity of the purchasing power parity hypothesis: The case of Türkiye. Cumhuriyet Üniversitesi İktisadi ve İdari Bilimler Dergisi, 27(1), 38–53. https://doi.org/10.37880/cumuiibf.1749539
Yang, D., Li, Y., Guo, J., Li, G., & Sun, S. (2023). Regional tourism demand forecasting with spatiotemporal interactions: A multivariate decomposition deep learning model. Asia Pacific Journal of Tourism Research, 28(6), 625–646. https://doi.org/10.1080/10941665.2023.2256431
Zhang, S., Lin, Z., & Yhang, W. (2025). Forecasting international tourist arrivals in South Korea: A deep learning approach. Journal of Hospitality and Tourism Technology, 16(2), 247–268. https://doi.org/10.1108/JHTT-03-2024-0176
Zhang, Y., Li, G., Muskat, B., & Law, R. (2021). Tourism demand forecasting: A decomposed deep learning approach. Journal of Travel Research, 60(5), 981–997. https://doi.org/10.1177/0047287520919522
Zhang, Y., Tan, W. H., & Zeng, Z. (2025). Tourism demand forecasting based on a hybrid temporal neural network model for sustainable tourism. Sustainability, 17(5), 2210. https://doi.org/10.3390/su17052210
Zheng, S., & Zhang, Z. (2023). Adaptive tourism forecasting using hybrid artificial intelligence model: A case study of Xi'an international tourist arrivals. PeerJ Computer Science, 9, e1573. https://doi.org/10.7717/peerj-cs.1573
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Tourism & Gastronomy Studies
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
