From Causes to Forecasts: Granger Causality and Machine Learning Predictions of Housing Sales in Türkiye

Yıl 2025, Cilt: 75 Sayı: 2, 432 - 452, 15.01.2026

Musa Gün , Ahmet Akusta , Haydar Karadağ

https://doi.org/10.26650/ISTJECON2025-1707729

https://izlik.org/JA68XZ23SF

Öz

This study aims to examine the impact of macro-financial indicators on the housing sales volume in Türkiye and evaluate the forecasting performance of traditional time-series models versus modern machine-learning algorithms. Using monthly data from January 2014 to November 2024, the research uses linear and non-linear Granger causality tests to investigate the lagged effects of 13 economic variables, including mortgage rates, loan volume, housing price indices, inflation, industrial production, consumer confidence, and unemployment. The findings reveal statistically significant causal relationships between housing sales and several indicators, notably interest rates, housing prices, consumer prices, and industrial output. These links imply that the cyclical effects of credit conditions, price expectations, or real-sector activity on housing demand operate with relatively short time lags. The predictive performance was evaluated using six models, including a multilayer perceptron, random forest, polynomial regression, gradient boosting, seasonal LSTM, and SARIMAX. Considering the test MAPE, the neural-network models provide the best predictions, with the multilayer perceptron and the seasonal LSTM obtaining MAPEs of 17.3% and 19.7%, respectively. On the other hand, the SARIMAX and tree-type models have worse generalisation capability. The results demonstrate the value of combining causal analysis with advanced forecasting to capture the dynamics of the housing market. They provide a practical framework for anticipating changes in demand and support the integration of machine-learning tools into economic monitoring and policy evaluation. This dual approach enhances the understanding of how economic conditions propagate through the housing sector and contributes to more informed housing market governance.

Anahtar Kelimeler

Real Estate Prices , Housing Sales , Machine Learning Algorithms

Kaynakça

• Adetunji, A. B., Akande, O. N., Ajala, F. A., Oyewo, O., Akande, Y. F., & Oluwadara, G. (2022). House price prediction using the random forest machine learning technique. Procedia Computer Science, 199, 806-813. doi:10.1016/j.procs.2022.01.100. google scholar
• Akkaya, M. (2024). Konut fiyat balonu ve konut fiyatını etkileyen faktörlerin analizi: Türkiye uygulaması. Gazi İktisat ve İşletme Dergisi, 10 (1), 33-45. https://doi.org/10.30855/gjeb.2024.10.1.003. google scholar
• Akusta, A. (2024). Konut Piyasası Trendlerinin Çözümlenmesi: Türkiye’de Toplam Konut Satışlarının Tahmini. Necmettin Erbakan Üniversitesi Siyasal Bilgiler Fakültesi Dergisi, 6 (1), 113-127. doi:10.51124/jneusbf.2024.78.google scholar
• Antonakakis, N., Gupta, R. André, C. (2015). Dynamic co-movements between economic policy uncertainty and housing market returns. Journal of Real Estate Portfolio Management, 21 (1), 53–60. https://doi.org/10.1080/10835547.2015.12089971. google scholar
• Atasoy, T. and Tursun, A. (2022). An Analysis of the Housing Market and First Sales of Houses in Turkey Eurasian Business & Economics Journal, 29, 23-40. google scholar
• Baker, S., Bloom, N. Davis, S. J. (2012). Has Economic Policy Uncertainty Hampered the Recovery? Working Paper, No. 242, The University of Chicago, George J. Stigler Centre for the Study of the Economy and the State, Chicago. google scholar
• Baldominos, A., Blanco, I., Moreno, A. J., Iturrarte, R., Bernárdez, Ó., & Afonso, C. (2018). Identifying Real Estate Opportunities Using Machine Learning Applied Sciences, 8(11), 2321. doi:10.3390/app8112321. google scholar
• Barr, J. R., Ellis, E. A., Kassab, A., Redfearn, C. L., Srinivasan, N. N., & Voris, K. B. (2017). Home price index: a machine learning methodology International Journal of Semantic Computing, 11(01), 111-133. doi: 10.1142/S1793351X17500015. google scholar
• Bin, O. (2004). Prediction comparison of housing sales prices by parametric versus semi-parametric regressions. Journal of Housing Economics, 13 (1), 68-84. doi:10.1016/j.jhe.2004.01.001. google scholar
• Branch, W. A., Nadeau, N. P. Rocheteau, G. (2016). Financial frictions, the housing market, and unemployment. Journal of Economic Theory, 164, 101-135. https://doi.org/10.1016/j.jet.2015.07.008. google scholar
• Broulíková, H. M., Huber, P., Montag, J. Sunega, P. (2020). Homeownership, mobility, and unemployment: Evidence from housing privatisation. Journal of Housing Economics, 50, 101728. doi:10.1016/j.jhe.2020.101728.google scholar
• Caplin, A., Chopra, S., Leahy, J. V., LeCun, Y. and Thampy, T. (2008). Machine learning and the spatial structure of house prices and housing returns Available at: http://dx.doi.org/10.2139/ssrn.1316046. google scholar
• Central Bank of Republic of Türkiye (CBRT). (2025). Electronic Data Delivery System (EDDS). https://evds2.tcmb.gov.tr/index.php. google scholar
• Çepi, O., Gupta, R. & Wohar, M. E. (2019). The role of real estate uncertainty in predicting US home sales growth: evidence from a quantiles-based Bayesian model averaging approach Applied Economics, 52 (5), 528–536. doi:10.1080/00036846.2019.1654082. google scholar
• Chen, Y., Jiao, J., & Farahi, A. (2023). Disparities in affecting factors of housing price: A machine learning approach to the effects of housing status, public transit, and density factors on single-family housing price. Cities, 140, 104432. https://doi.org/10.1016/j. cities.2023.104432. google scholar
• Çılgın, C., & Gökçen, H. (2023). Machine learning methods for predicting real estate sales prices in Turkey. Revista de la construcción, 22(1), 163-177. https://dx.doi.org/10.7764/rdlc.22.1.163. google scholar
• De Amorim, L. B. V., Cavalcanti, G. D. C., & Cruz, R. M. O. (2024). Meta-scaler: A meta-learning framework for the selection of scaling techniques. IEEE Transactions on Neural Networks and Learning Systems. doi: 10.1109/TNNLS.2024.3366615. google scholar
• Díaz, A. and Jerez, B. (2013). House Prices, Sales, and Time on the Market: A Search-Theoretic Framework International Economic Review, 54, 837-872. https://doi.org/10.1111/iere.12019. google scholar
• Erkek, M. E. H. M. E. T., Çayırlı, K., & Hepsen, A. (2020). Predicting house prices in Turkey using machine learning algorithms Journal of Statistical and Econometric Methods, 9(4), 31-38. google scholar
• Foryś, I. (2022). Machine learning in-house price analysis: regression models versus neural networks Procedia Computer Science, 207, 435-445. doi:10.1016/j.procs.2022.09.078. google scholar
• Harding, J. P., Rosenthal, S. S. Sirmans, C. F. (2007). Depreciation of housing capital, maintenance, and house price inflation: Estimates from a repeat sales model. Journal of Urban Economics, 61 (2), 193-217. doi:10.1016/j.jue.2006.07.007. google scholar
• Huang, X. (Ivy). (2017). Productivity, model uncertainty, and the new home sales price in the U.S. http://dx.doi.org/10.2139/ssrn.3566787. google scholar
• Kang, W. (2011). Missing-data imputation in nonstationary panel data models. In D. M. Drukker (Ed.), Advances in Econometrics (C. 27, pp. 235-251). Emerald Group Publishing Limited. https://doi.org/10.1108/S0731-9053(2011)000027B007. google scholar
• Karadağ, H. (2021). Türkiye Ekonomisinde Bankalar Tarafından Verilen Konut Kredileri, Konut Satışları ve İşsizlik Arasındaki İlişki (2010:Q1-2020:Q3). Journal of Social Policy Conferences, 80, 403-422. https://doi.org/10.26650/jspc.2021.80.001609. google scholar
• Kılcı, E. N. (2019). Konut Kredisi Faiz Oranları ile İpotekli Konut Satışları Arasındaki İlişkinin Analizi; Türkiye Örneği. Turkish Studies -Economics, Finance, Politics, 14 (1), 95-107. https://dx.doi.org/10.7827/TurkishStudies.15033. google scholar
• Li, G., Wang, P. Zhang, Q. (2018). Market thickness and the impact of unemployment on housing market outcomes Journal of Monetary Economics, 98, 27-49. doi:10.1016/j.jmoneco.2018.04.007. google scholar
• Liu, Y., Li, Y., Xu, Z., Liu, X., Xie, H. and Zeng, H. (2023). Guided dropout: Improving deep networks without increased computation. Intelligent Automation & Soft Computing, 36(3), 2519-2528. doi:10.32604/iasc.2023.033286. google scholar
• Macêdo, D., Zanchettin, C., & Ludermir, T. (2024). Sigmoidal learning rate optimiser for deep neural network training using a two-phase adaptation approach. Appl Soft Comput, 167, 112264. https://doi.org/10.1016/j.asoc.2024.112264. google scholar
• Maciej Rosoł, Marcel Młyńczak, Gerard Cybulski (2022). Granger causality test with nonlinear eural-network-based methods: Python package and simulation study. Computer Methods and Programmes in Biomedicine, 216. https://doi.org/10.1016/j.cmpb.2022. 106669. google scholar
• Montaha S, Azam S, Rafid Akmrh, Islam S, Ghosh P, Jonkman M (2022) A shallow deep learning approach to classify skin cancer using down-scaling method to minimise time and space complexity. PLoS ONE 17(8): e0269826. https://doi.org/10.1371/journal.pone. 0269826. google scholar
• Mora-Garcia, R.-T., Cespedes-Lopez, M.-F., & Perez-Sanchez, V. R. (2022). Housing Price Prediction Using Machine Learning Algorithms in COVID-19 Times. Land, 11(11), 2100. doi:10.3390/land11112100. google scholar
• Oikarinen, E. (2012). Empirical evidence on the reaction speeds of housing prices and sales to demand shocks Journal of Housing Economics, 21 (1), 41-54. doi:10.1016/j.jhe.2012.01.004. google scholar
• Oner, S. (2022). The effect of real effective usd/try exchange rate on tourism income: An empirical analysis of Turkey. Journal of Tourism Management Research, 9(2), 97-109. doi:10.18488/31.v9i2.3080. google scholar
• Özçim, H. (2022). Türkiye’deki konut satışı ile TCMB politika faiz oranı ve konut fiyat endeksi arasındaki ilişkinin analizi. Nevşehir Hacı Bektaş Veli Üniversitesi Sosyal Bilimler Enstitüsü Dergisi, 12 (1), 523-533. https://doi.org/10.30783/nevsosbilen.1074220. google scholar
• Papana, A., Kyrtsou, C., Kugiumtzis, D., & Diks, C. (2022). Identification of causal relationships in non-stationary time series with an information measure: Evidence for simulated and financial data. Empirical Economics. doi:10.1007/s00181-022-02275-9. google scholar
• Park, B. and Bae, J. K. (2015). Using machine learning algorithms for housing price prediction: The case of Fairfax County, Virginia housing data. Expert systems with applications, 42(6), 2928-2934. doi:10.1016/j.eswa.2014.11.040. google scholar
• Petersen, A. M. (2024). How much did the pandemic uncertainty affect real-estate speculation? Evidence from the on-market valuation of for-sale versus rental properties. Applied Economics Letters, 1–5. doi:10.1080/13504851.2024.2302898. google scholar
• Rafiei, M. H. and Adeli, H. (2016). A novel machine learning model for estimating the sale prices of real estate units. Journal of Construction Engineering and Management, 142(2), 04015066. doi:10.1061/(ASCE)CO.1943-7862.0001047. google scholar
• Reed, R. R. Ume, E. S. (2016). Housing and unemployment: The search for the “American Dream.” Journal of Macroeconomics, 48, 72-86. doi:10.1016/j.jmacro.2016.01.001. google scholar
• Rico-Juan, J. R., & de La Paz, P. T. (2021). Machine learning with explainability or spatial hedonics tools? An analysis of the asking prices in the housing market in Alicante, Spain Expert Systems with Applications, 171, 114590. doi:10.1016/j.eswa.2021.114590. google scholar
• Riley, S. F., Nguyen, G. Manturuk, K. (2015). House price dynamics, unemployment, and the mobility decisions of low-income homeowners. Housing and the Built Environment., 30, 141–156. https://doi.org/10.1007/s10901-014-9400-y. google scholar
• Santhanakrishnan, K., & Senthooran, V. (2022). A parallel distributed cluster computing model for Z-score computation regarding Sri Lankan university admissions. In ICARC 2022-2nd International Conference on Advanced Research in Computing: Towards a Digitally Empowered Society (pp. 344–348). doi: 10.1109/ICARC54489.2022.9754093. google scholar
• Selci, Y. B. (2021). Türkiye’nin Konut Satışı Değerlerinin Yapay Sinir Ağları ile Öngörülmesi. EKOIST Journal of Econometrics and Statistics, 35, 19-32. doi:10.26650/ekoist.2021.35.180033. google scholar
• Seth, S. and Principe, J. C. (2012). Assessing granger non-causality using nonparametric measure of conditional independence. IEEE Transactions on Neural Networks and Learning Systems, 23(1), 47-59. https://doi.org/10.1109/TNNLS.2011.2178327. google scholar
• Sobieraj, J., & Metelski, D. (2024). Machine Learning Insights: Exploring Key Factors Influencing the Sale-to-List Ratio—Insights from SVM Classification and Recursive Feature Selection in the US Real Estate Market Buildings, 14(5), 1471. https://doi.org/10.3390/ buildings14051471.google scholar
• Sun, N. (2021). Effects of Housing Price on Unemployment Rate and Stock Market International Journal of Trade, Economics and Finance, 12 (5), 131-137. https://doi.org/10.18178/ijtef.2021.12.5.707. google scholar
• Tchuente, D., & Nyawa, S. (2022). Real estate price estimation in French cities using geocoding and machine learning Annals of Operations Research, 308(1), 571-608. doi:10.1007/s10479-021-03932-5. google scholar
• Truong, Q., Nguyen, M., Dang, H., & Mei, B. (2020). Housing price prediction via improved machine learning techniques Procedia Computer Science, 174, 433-442. doi:10.1016/j.procs.2020.06.111. google scholar
• Turkish Statistical Institute. (2025). https://data.tuik.gov.tr/. google scholar
• Varma, A., Sarma, A., Doshi, S. and Nair, R. (2018). House price prediction using machine learning and neural networks In 2018 Second International Conference on Inventive Communication and Computational Technologies (ICICCT), 1936-1939. https://10.1109/ ICICCT.2018.8473231.google scholar
• Viktorovich, P. A., Aleksandrovich, P. V., Leopoldovich, K. I. and Vasilevna, P. I. (2018). Predicting sales prices of the houses using regression methods of machine learning. 3rd Russian-Pacific Conference on Computer Technology and Applications (RPC), Vladivostok, Russia, 2018, pp. 1-5, https://10.1109/RPC.2018.8482191. google scholar
• Wheaton, W. C. Lee, N. J. (2009). The Co-Movement of Housing Sales and Housing Prices: Empirics and Theory (March 1, 2009). MIT Department of Economics Working Paper No. 09-05. http://dx.doi.org/10.2139/ssrn.1353590.google scholar
• World Uncertainty Index (2025). https://worlduncertaintyindex.com/.google scholar
• Yalçın, M. (2020). Türkiye Konut Satış İstatistiklerinin CBS Tabanlı Analizleri. Afyon Kocatepe Üniversitesi Fen ve Mühendislik Bilimleri Dergisi, 20 (3), 448-455. doi:10.35414/akufemubid.673133. google scholar
• Yardımcı, M. C. (2021). Türkiye’de Konut Satışları ve Ekonomik Büyüme Arasındaki İlişkinin Analizi. Ekonomi İşletme Siyaset ve Uluslararası İlişkiler Dergisi, 7(2), 380-391. google scholar
• Yazdani, M. (2021). Machine learning, deep learning, and hedonic methods for real estate price prediction. arXiv preprint arXiv:2110.07151. https://doi.org/10.48550/arXiv.2110.07151. google scholar
• Ying, X. (2019). An overview of overfitting and its solutions. Journal of Physics: Conference Series, 1168, 022022. https://doi.org/10.1088/ 1742-6596/1168/2/022022. google scholar
• Zhang, L., Shi, D., Chang, X., & Wen, H. (2021). Timing decisions of housing sales and development based on the real option theory. International Journal of Strategic Property Management, 25 (2), 90-101. https://doi.org/10.3846/ijspm.2020.13973. google scholar