ISTANBUL KONUT FİYATLARININ YAPAY ZEKA İLE TAHMİNLEMESİ: ARIMA VE LSTM KARŞILAŞTIRMASI

Year 2025, Volume: 27 Issue: 3, 235 - 252, 30.09.2025

Levent Sümer

https://doi.org/10.31460/mbdd.1668933

Abstract

Türkiye’de hane halkları, son yıllarda yüksek enflasyon nedeniyle yüksek konut fiyatlarıyla mücadele etmekte ve fiyat tahmini tekniklerinin konut yatırımı kararlarında yardımcı olabileceği düşünülmektedir. Bu çalışma, İstanbul konut fiyatlarını bir ekonometrik model olan ARIMA ve bir makine öğrenimi algoritması olan LSTM’yi karşılaştırarak tahminlemektedir. Ilk aşamada, yalnızca Türkiye Cumhuriyet Merkez Bankası'nın üç aylık ortalama konut birim fiyatları kullanılmıştır. İkinci aşamada modellere iki makroekonomik değişken, konut kredi faiz oranları ve enflasyon oranları (TÜFE) eklenmiştir. Analiz Sonuçlar, LSTM modelinden alınan tahminlerin ARIMA yaklaşımına göre daha başarılı olduğunu göstermiştir. Bu araştırma, yapay zekâ uygulamalarının sınırlı olduğu konut sektöründe önemli bir boşluğu doldurmayı amaçlamaktadır.

Keywords

ARIMA , LSTM , Yapay Zekâ , Konut Fiyat Tahminlemesi , Makine Öğrenmesi , ARIMA , LSTM

PREDICTING HOUSING PRICES IN ISTANBUL USING ARTIFICIAL INTELLIGENCE: A COMPARATIVE ANALYSIS OF ARIMA AND LSTM MODELS

Abstract

Due to high inflation, Türkiye has been struggling with high housing prices. This study compares two forecasting models: an econometric time-series model, ARIMA, and a machine learning algorithm, LSTM, in predicting housing prices in Istanbul. First, only the Central Bank’s quarterly average housing unit prices are used in both models. Second, two crucial macroeconomic variables, the mortgage loan interest rate and the inflation rate (as measured by the CPI), are added to the model. The results reveal that the forecast obtained from LSTM outperforms the ARIMA approach. This research fills a significant gap in the literature where the implementation of artificial intelligence in the housing industry is limited.

Keywords

ARIMA , LSTM , Artificial Intelligence , Housing Price Predictions , Machine Learning , ARIMA , LSTM

References

• Aktürk, C. (2020). Yapay Zekâ ile Konut Fiyatlarının Tahmin Edilmesi. Turkish Studies-Information Technologies and Applied Sciences. 15 (2), 183-194. 10.29228/TurkishStudies.43161.
• Albeladi, K., Zafar, B. & Mueen, A. (2023) “Time Series Forecasting using LSTM and ARIMA” International Journal of Advanced Computer Science and Applications(IJACSA), 14(1), http://dx.doi.org/10.14569/IJACSA.2023.0140133
• Alzain, E., Alshebami, A. S., Aldhyani, T. H. H., & Alsubari, S. N. (2022). Application of Artificial Intelligence for Predicting Real Estate Prices: The Case of Saudi Arabia. Electronics, 11(21), 3448. https://doi.org/10.3390/electronics11213448
• Arf, C. (1959). Makine Düşünebilir mi ve Nasıl Düşünebilir? Atatürk Üniversitesi 1958-1959 Öğretim Yılı Halk Konferansları (1), 91-103.
• Box, G.E.P. & Jenkins, G.M. (1976). Time Series Analysis: Forecasting and Control. 2nd Edition, Holden-Day, S. Francisco.
• Burhan, H. A. (2023). Konut Fiyatları Tahmininde Makine Öğrenmesi Sınıflandırma Algoritmalarının Kullanılması: Kütahya Kent Merkezi Örneği. Dumlupınar Üniversitesi Sosyal Bilimler Dergisi (76), 221-237. https://doi.org/10.51290/dpusbe.1249461
• CBRT (2024). All Series Statistics. Available at https://evds2.tcmb.gov.tr/index.php?/evds/serieMarket. Accessed on March 19, 2025.
• Conway, J. (2018). Artificial Intelligence and Machine Learning: Current Applications in Real Estate, Master Thesis. Massachusetts Institute of Technology.
• Gupta, M. (2024). What is LSTM (Long Short Term Memory)? Available at https://www.appliedaicourse.com/blog/lstm-in-machine-learning/. Accessed on September 17, 2025.
• Haque, D. (2024). Transforming Japan real estate, arXiv:2405.20715v1, https://doi.org/10.48550/arXiv.2405.20715
• Kang, J., Lee, H. J., Jeong, S. H., Lee, H. S., & Oh, K. J. (2020). Developing a Forecasting Model for Real Estate Auction Prices Using Artificial Intelligence. Sustainability, 12(7), 2899. https://doi.org/10.3390/su12072899
• Kayakuş, M., Terzioğlu, M., & Yetiz, F. (2022) Forecasting housing prices in Turkey by machine learning methods. Aestimum 80: 33-44. doi: 10.36253/aestim-12320
• Kontopoulou, V. I., Panagopoulos, A. D., Kakkos, I., & Matsopoulos, G. K. (2023). A Review of ARIMA vs. Machine Learning Approaches for Time Series Forecasting in Data Driven Networks. Future Internet, 15(8), 255. https://doi.org/10.3390/fi15080255
• Makridakis S., & Hibon M. (1997). ARMA Models and the Box-Jenkins Methodology, Journal of Forecasting, 16: 147-163.
• Mangaleswaran, S., Vigneshwari, S. (2020). Prediction of Housing Prices Using Machine Learning, Time Series ARIMA Model and Artificial Neural Network. In: Kumar, A., Paprzycki, M., Gunjan, V. (eds) ICDSMLA 2019. Lecture Notes in Electrical Engineering, vol 601. Springer, Singapore. https://doi.org/10.1007/978-981-15-1420-3_110
• Monika, R., Nithyasree, J., Valarmathi V., Hemalakshmi, G. R., Prakash, N. B. (2021), House Price Forecasting Using Machine Learning Methods, Turkish Journal of Computer and Mathematics Education, 12(11), 3624-3632.
• Muggleton, S. (2014). Alan Turing and the development of Artificial Intelligence. AI Communications, 27(1), 3-10. https://doi.org/10.3233_AIC-130579
• OECD (2024). Housing Prices. Available at https://www.oecd.org/en/data/indicators/housing-prices.html?oecdcontrol-82d381eddd-var3=1947. Accessed on March 19, 2025.
• Pan, Y. (2016). Heading toward Artificial Intelligence 2.0, Engineering, 2(4), 409-413, ISSN 2095-8099, https://doi.org/10.1016/J.ENG.2016.04.018.
• Park, B., Bae, J. K. (2015). Using machine learning algorithms for housing price prediction. Expert Syst. Appl. 42(6), 2928–2934. https://doi.org/10.1016/j.eswa.2014.11.040
• Rampini, L., Re Cecconi, F. (2022). Artificial intelligence algorithms to predict Italian real estate market prices, Journal of Property Investment & Finance, 40(6), 588-611, DOI 10.1108/JPIF-08-2021-0073
• Rossini, P. (2000). Using Expert Systems and Artificial Intelligence For Real Estate Forecasting, Sixth Annual Pacific-Rim Real Estate Society Conference, Sydney, Australia, 1-10.
• Siami-Namini, S., Tavakoli, N., Siami Namin A. (2019). A Comparative Analysis of Forecasting Financial Time Series Using ARIMA, LSTM, and BiLSTM, https://doi.org/10.48550/arXiv.1911.09512
• Sümer, L. (2017). Developing a Real Estate-Pension Fund Investment Ecosystem: Turkey Real Estate Fund. Ph.D. Thesis, Boğaziçi University.
• Thakur, D. (2018). LSTM and its equations. Available at https://medium.com/@divyanshu132/lstm-and-its-equations-5ee9246d04af. Accessed on March 19, 2025.
• Trindade Neves, F., Aparicio, M., & de Castro Neto, M. (2024). The Impacts of Open Data and eXplainable AI on Real Estate Price Predictions in Smart Cities. Applied Sciences, 14(5), 2209. https://doi.org/10.3390/app14052209
• Truong, Q., Nguyen M., Dang, H., Mei, B. (2020). Housing Price Prediction via Improved Machine Learning Techniques, Procedia Computer Science, 174, 433-442, ISSN 1877-0509, https://doi.org/10.1016/j.procs.2020.06.111.
• Turing, A. M. (1950). Computing Machinery and Intelligence. Mind 49: 433-460.
• Viriato, J. C. (2019). AI and Machine Learning in Real Estate Investment, The Journal of Portfolio Management Special Real Estate, 45( 7), 43 – 54, DOI: 10.3905/jpm.2019.45.7.043
• Winky, K.O. H, Bo-Sin, T. & Siu, W. W. (2021). Predicting property prices with machine learning algorithms, Journal of Property Research, 38(1), 48-70, DOI: 10.1080/09599916.2020.1832558
• Xie, M. (2019). Development of Artificial Intelligence and Effects on Financial System, Journal of Physics: Conference Series,1187, 032084
• Zakaria, S., Abdul Manaf, S. M., Amron, M. T., & Mohd Suffian, M. T. (2023). Has the World of Finance Changed? A Review of the Influence of Artificial Intelligence on Financial Management Studies. Information Management and Business Review, 15(4(SI)I), 420-432. https://doi.org/10.22610/imbr.v15i4(SI)I.3617
• Zhang, C., Yang, Lu. (2021). Study on artificial intelligence: The state of the art and future prospects, Journal of Industrial Information Integration, 23 (100224). Volume 23, 100224, ISSN 2452-414X, https://doi.org/10.1016/j.jii.2021.100224