BÖLGESEL KONUT PİYASASI VERİLERİ İLE YENİ KİRACI KİRA ENDEKSİ TAHMİNİ: TOPLULUK ÖĞRENME ALGORİTMALARI YAKLAŞIMI

Öz

Küreselleşme ve artan şehirleşme hızıyla birlikte konut piyasaları, barınma ihtiyacının ötesinde stratejik bir yatırım aracı ve ekonomik dengenin temel belirleyicisi haline gelmiştir. Türkiye özelinde pandemi, 6 Şubat depremleri ve döviz kuru hareketliliği gibi dışsal şoklar, mevcut kira sözleşmeleri ile piyasadaki gerçek değerler arasında ciddi farklar oluşturarak ‘yeni kiracı kira endeksi’ verilerinin analizini kritik hale getirmiştir. Bu çalışmanın amacı, Türkiye’deki yeni kiracı kira endeksi değerlerini topluluk öğrenme algoritmalarıyla analiz etmek ve 2026 yılının ilk altı ayına yönelik tahminler üretmektir. Araştırma kapsamında, Türkiye Cumhuriyet Merkez Bankası (TCMB) veri sisteminden alınan Ocak 2018- Aralık 2025 dönemine ait aylık veriler kullanılmıştır. Analizlerde Artımlı Öğrenme Tabanlı Destek Vektör Regresyonu (AR-DVR) ve Tarafsız Öznitelik Seçilmiş Sınıflandırıcı Destek Vektör Regresyonu (UAS-DVR) algoritmalarından yararlanılmıştır. Bulgular, AR-DVR modelinin %95.85 yönsel doğruluk ve 1.06 MAPE değeri ile başarılı performans sergilediğini göstermiştir. İkili Korelasyon Tabanlı Öznitelik Seçim Algoritması sonuçlarına göre, İstanbul, İzmir, Adana-Mersin, Kocaeli havzası ve Bursa-Eskişehir gruplarının yeni kiracı kira endeksi üzerinde en yüksek belirleyiciliğe sahip merkezler olduğu saptanmıştır. Çalışma, veri sadeleştirilmesine rağmen algoritmaların yüksek başarı oranlarını koruduğunu ve geliştirilen hibrit yaklaşımların kira piyasası tahminlerinde sürdürülebilir bir karar destek aracı olarak kullanılabileceğini ortaya koymaktadır.

Anahtar Kelimeler

• Yeni Kiracı Kira Endeksi
• Topluluk öğrenmesi
• Tahminleme
• Türkiye

PREDICTING NEW TENANT RENT INDEX WITH REGIONAL HOUSING MARKET DATA: AN ENSEMBLE LEARNING ALGORITHMS APPROACH

Öz

As globalization and rapid urbanization accelerate, housing markets have evolved beyond mere shelter into strategic investment vehicles and key determinants of economic stability. In the specific context of Turkey, external shocks such as the pandemic, the February 6 earthquakes, and exchange rate volatility have created a significant gap between existing lease agreements and actual market values, making the analysis of 'new tenant rent index' data critical. This study aims to analyze Turkey's new tenant rent index values using ensemble learning algorithms and to generate predicting for the first six months of 2026. The research utilizes monthly data from January 2018 to December 2025, sourced from the Central Bank of the Republic of Turkey (CBRT). The analysis employs Additive Regression-based Support Vector Regression (AR-SVR) and Unbiased Attribute Selected Classifier Support Vector Regression (UAS-SVR) algorithms. Findings indicate that the AR-SVR model performed successfully, achieving 95.85% directional accuracy and a MAPE value of 1.06. According to the results of the Pairwise Correlation Feature Selection Algorithm, Istanbul, Izmir, the Adana-Mersin region, the Kocaeli basin, and the Bursa-Eskisehir groups were identified as the most influential centers for the new tenant rent index. The study reveals that the algorithms maintain high success rates despite data reduction, demonstrating that the developed hybrid approaches can serve as sustainable decision-support tools for rental market predicting.

Anahtar Kelimeler

• New Tenant Rent Index
• Ensemble Learning
• Predicting
• Türkiye

Kaynakça

1. Abioğlu, V. (2020). Türkiye konut piyasasinda balon oluşumlari: bölgesel inceleme. Finansal Araştırmalar ve Çalışmalar Dergisi, 12(22), 1-14. https://doi.org/10.14784/marufacd.688444
2. Adams, B., Loewenstein, L., Montag, H., & Verbrugge, R. (2024). Disentangling rent index differences: data, methods, and scope. American Economic Review: Insights, 6(2), 230-245. https://doi.org/10.1257/aeri.20220685
3. Ambrose, B. W., Coulson, N. E., & Yoshida, J. (2015). The repeat rent index. Review of Economics and Statistics, 97(5), 939-950. https://doi.org/10.1162/REST_a_00500
4. Chacon, R. G. (2023). Tenant concentration in REITs. The Journal of Real Estate Finance and Economics, 66(3), 636-679. https://doi.org/10.1007/s11146-021-09829-1
5. Chen, Y., Liu, X., Li, X., Liu, Y., & Xu, X. (2016). Mapping the fine-scale spatial pattern of housing rent in the metropolitan area by using online rental listings and ensemble learning. Applied Geography, 75, 200-212. https://doi.org/10.1016/j.apgeog.2016.08.011
6. Clark, T. E., Huber, F., Koop, G., Marcellino, M., & Pfarrhofer, M. (2023). Tail forecasting with multivariate Bayesian additive regression trees. International Economic Review, 64(3), 979-1022. https://doi.org/10.1111/iere.12619
7. Cotton, C. D. (2026). Understanding CPI shelter inflation: The importance of the new-tenant/all-tenant rent gap. Journal of Housing Economics, 102117. https://doi.org/10.1016/j.jhe.2025.102117
8. Durmuş, A. (2025). Türkiye’de Konut Kiraları ve Enflasyon: 2005–2025 Dönemi. Maltepe Üniversitesi Akademik Bakış Dergisi, 1(2), 90-101. https://izlik.org/JA93AZ97XD

9. Filiz, E. (2026). Prediction of the Gross Electricity Generation Amount with Energy Sources Using the M5P Decision Tree Algorithm. Kırklareli Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, 15(1), 1-18. https://doi.org/10.53306/klujfeas.1841997
10. Friedman, J. H. (2002). Stochastic gradient boosting. Computational statistics & data analysis, 38(4), 367-378. https://doi.org/10.1016/S0167-9473(01)00065-2
11. Geng, X., Shi, Y., Ou, Y., & Yin, F. (2025). Probabilistic forecasting of hand, foot and mouth disease in Mainland China using bayesian additive regression tree model. Scientific Reports, 15(1), 33745. https://doi.org/10.1038/s41598-025-98954-5
12. Gill, R., Kalwar, S., & Memon, I. A. (2020). Yeh’s satisfaction Index modelling of tenants in rental appartments (A case study of Latifabad Hyderabad). Sukkur IBA Journal of Computing and Mathematical Sciences, 4(2), 1-10. https://doi.org/10.30537/sjcms.v4i2.654
13. Hoffmann, J., & Kurz, C. (2002). Rent indices for housing in West Germany 1985 to 1998 (No. 116). ECB Working Paper. https://hdl.handle.net/10419/152550
14. Hu, G., & Tang, Y. (2023). GERPM: A Geographically Weighted Stacking Ensemble Learning-Based Urban Residential Rents Prediction Model. Mathematics, 11(14), 3160. https://doi.org/10.3390/math11143160
15. Jiménez, F., Sánchez, G., Palma, J., Miralles-Pechuán, L., & Botía, J. (2021). Multivariate feature ranking of gene expression data. arXiv preprint arXiv:2111.02357. https://doi.org/10.48550/arXiv.2111.02357
16. Kutsal, S., & Polatoğlu, Ç. (2023). Türkiye’de artan konut ihtiyacı ve konut sorununun dinamikleri. Topkapı Sosyal Bilimler Dergisi, 2(1), 133-158. https://izlik.org/JA97AE52YA
17. Larsen, E. R., & Sommervoll, D. E. (2009). The impact on rent from tenant and landlord characteristics and interaction. Regional Science and Urban Economics, 39(3), 316-322. https://doi.org/10.1016/j.regsciurbeco.2008.10.004
18. Lee, S., & Kim, K. M. (2025). A Study on the Estimation of Apartment Rent Index Using Machine Learning. Journal of Real Estate Analysis, 11(1), 19-42. https://doi.org/10.30902/jrea.2025.11.1.19
19. Lin, B., & Xu, B. (2020). How does fossil energy abundance affect China's economic growth and CO2 emissions?. Science of the Total Environment, 719, 137503. https://doi.org/10.1016/j.scitotenv.2020.137503
20. Liu, C., Shao, B., Zhao, W., Zeng, H., Tian, N., Zhao, X., & Liu, X. (2026). Rental Property Recommendation System Based on Fuzzy Decision Tree. Computational Intelligence, 42(2), e70220. https://doi.org/10.1111/coin.70220
21. Loewenstein, L., Meyer, J., & Verbrugge, R. J. (2024). New-tenant rent passthrough and the future of rent inflation. Economic Commentary, (2024-17). https://doi.org/10.26509/frbc-ec-202417
22. Louzada, F., de Lacerda, K. J. C. C., Ferreira, P. H., & Gomes, N. D. (2025). Smart renting: harnessing urban data with statistical and machine learning methods for predicting property rental prices from a tenant’s perspective. Stats, 8(1), 12. https://doi.org/10.3390/stats8010012
23. Maheshwari, A., Ranka, M., Malhotra, A., Mishra, R. K., & Basha, M. S. A. (2024, November). Assessing Machine Learning Models for Predictive Analytics in Urban Rental Markets: Rent Price Forecasting in India. In 2024 International Conference on Integrated Intelligence and Communication Systems (ICIICS) (ss. 1-9). IEEE. https://doi.org/10.1109/ICIICS63763.2024.10859514
24. Ming, Y., Zhang, J., Qi, J., Liao, T., Wang, M., & Zhang, L. (2020, September). Prediction and analysis of chengdu housing rent based on xgboost algorithm. In Proceedings of the 3rd International Conference on Big Data Technologies (ss. 1-5). https://doi.org/10.1145/3422713.3422720
25. Neloy, A. A., Haque, H. S., & Ul Islam, M. M. (2019, February). Ensemble learning based rental apartment price prediction model by categorical features factoring. In Proceedings of the 2019 11th International conference on machine learning and computing (ss. 350-356). https://doi.org/10.1145/3318299.3318377
26. Nussli, E., Arulraj-Cordonier, R., Strasser, F., Nanut Petric, M., Bech, M. L., & Pipino, A. (2026). From listings to all-tenant rents: A probabilistic model (January 22, 2026). Swiss National Bank Working Paper No. 02/2026, https://dx.doi.org/10.2139/ssrn.6114986
27. Ogundunmade, T. P., Abidoye, M., & Olunfunbi, O. M. (2023). Modelling Residential Housing Rent Price Using Machine Learning Models. Mod Econ Manag, 2. https://doi.org/10.53964/mem.2023014
28. Shevade, S. K., Keerthi, S. S., Bhattacharyya, C., & Murthy, K. R. K. (2000). Improvements to the SMO algorithm for SVM regression. IEEE Transactions on Neural Networks, 11(5), 1188-1193. https://doi.org/10.1109/72.870050
29. Smola, A. J., & Schölkopf, B. (2004). A tutorial on support vector regression. Statistics and computing, 14(3), 199-222. https://doi.org/10.1023/B:STCO.0000035301.49549.88
30. Suman, A., & Singh, R. B. (2025, June). Rent Sense: Integrating Ensemble Method, Geo-Spatial Model and Time Series Model to Navigate Rental Decision Across Metropolitan Cities. In 2025 International Conference on Computing Technologies (ICOCT) (pp. 1-8). IEEE. https://doi.org/10.1109/ICOCT64433.2025.11118847
31. TCMB. (2026). Sanayi Üretim Endeksi, https://evds3.tcmb.gov.tr/tumSeriler/2003/bie_ykke, (Erişim Tarihi: 15.04.2026).
32. Webb, R. B., & Fisher, J. D. (1996). Development of an effective rent (lease) index for the Chicago CBD. Journal of urban Economics, 39(1), 1-19. https://doi.org/10.1006/juec.1996.0001
33. Weka. (2026). weka.classifiers.meta.UnbiasedAttributeSelectedClassifier, https://weka.sourceforge.io/doc.dev/weka/classifiers/meta/AttributeSelectedClassifier.html. (Erişim Tarihi: 20.04.2026).
34. Witten, I. H., Frank, E., Hall, M. A., Pal, C. J., & Data, M. (2005, June). Practical machine learning tools and techniques. In Data mining (Cilt. 2, Sayı. 4, ss. 403-413). Amsterdam, The Netherlands: Elsevier.