USE OF MACHINE LEARNING AND DEEP LEARNING METHODS IN HOUSING PRICE INDEX ESTIMATION: AN ANALYSIS ON ANKARA AND ISTANBUL

Yıl 2024, , 1345 - 1353, 18.09.2024

Ahmed İhsan Şimşek

https://doi.org/10.18069/firatsbed.1401213

Öz

Factors such as supply chain difficulties, rising energy and oil prices, economic recession and production loss due to the pandemic have increased costs and inflation. All these factors have also seriously affected the construction sector. This study aims to create a deep learning and machine learning focused forecasting system based on Istanbul and Ankara monthly housing price index data for the period of January 2010 to June 2023. The system was created using approximately 13 years of housing interest rates, Consumer Price Index, XGMYO, Monthly Average Dollar and XAU data as the basis of the Istanbul and Ankara Housing Price Index forecasting process. During the research process, different RNN structures (Long and Short Term Memory, Gated Recurrent Unit) and machine learning (Random Forest) structures were tested and the effectiveness of these structures in housing price index forecasting was compared. The performances of the models were evaluated using RMSE, MSE, MAE, MAPE and R2 statistics. According to the results obtained, the method that gave the best performance for both provinces is the RF model. This is followed by LSTM and GRU models, respectively

Anahtar Kelimeler

House Price Forecasting, Time Series, Deep Learning, Machine Learning, Decision Support

Konut Fiyat Endeksi Tahmininde Makine Öğrenmesi ve Derin Öğrenme Yöntemlerinin Kullanımı: Ankara ve İstanbul Üzerine Bir Analiz

Öz

Pandeminin etkisiyle tedarik zincirinde yaşanan zorluklar, enerji ve petrol fiyatlarının yükselmesi, ekonomik durgunluk ve üretim kaybı gibi faktörler, maliyetleri ve enflasyonu artırmıştır. Tüm bu etkenler inşaat sektörünü de ciddi biçimde etkilemiştir. Bu çalışma, Ocak 2010 ile Haziran 2023 dönemine ait İstanbul ve Ankara aylık konut fiyat endeksi verilerine dayalı olarak derin öğrenme ve makine öğrenmesi odaklı bir tahmin sistemi oluşturma amacını taşımaktadır. İstanbul ve Ankara Konut Fiyat Endeksi tahminleme işleminin temeli olarak yaklaşık 13 yıllık konut faizleri, Tüketici Fiyat Endeksi, XGMYO, Aylık Ortalama Dolar ve XAU verileri kullanılarak sistem oluşturulmuştur. Araştırma sürecinde, farklı RNN yapıları (Long and Short Term Memory, Gated Recurrent Unit) ve makine öğrenmesi (Random Forest) yapıları denenmiş, bu yapıların konut fiyat endeksi tahminindeki etkinliği karşılaştırılmıştır. Modellerin performansları RMSE, MSE, MAE, MAPE ve R2 istatistikleri kullanılarak değerlendirilmiştir. Elde edilen sonuçlara göre her iki il için en iyi performansı veren yöntem RF modelidir. Sonrasında ise sırasıyla LSTM ve GRU modelleri gelmektedir.

Anahtar Kelimeler

Konut Fiyat Tahmini, Zaman Serisi, Derin Öğrenme, Makine Öğrenmesi, Karar Destek

Kaynakça

• Adetunji, A. B., Akande, O. N., Ajala, F. A., Oyewo, O., Akande, Y. F., & Oluwadara, G. (2022). House Price Prediction Using Random Forest Machine Learning Technique. Procedia Computer Science, 199, 806-813.
• Akay, E. Ç., Topal, K. H., Kizilarslan, S., & Bulbul, H. (2019). Türkiye Konut Fiyat Endeksi Öngörüsü: ARIMA, Rassal Orman Ve Arima-Rassal Orman. Pressacademia Procedia, 10(1), 7-11.
• Breiman, L. 2001. Random Forests. Machine Learning 45: 5–32.
• Cho, M., Kim, C., Jung, K., & Jung, H. (2022). Water Level Prediction Model Applying A Long Short-Term Memory (Lstm)–Gated Recurrent Unit (Gru) Method For Flood Prediction. Water, 14(14), 2221.
• Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014). Empirical Evaluation Of Gated Recurrent Neural Networks On Sequence Modeling. Proceedings Of The Neural Information Processing Systems Workshop On Deep Learning., 1–9. Http://Arxiv.Org/Abs/1412.3555
• Çetin, D. T. (2022). Antalya-Isparta-Burdur Bölgesi Konut Fiyat Endeksinin Makroekonomik Göstergeler Ve Hisse Senedi Endeksi Kullanılarak Yapay Zekâ İle Tahmini. Abant Sosyal Bilimler Dergisi, 22(3), 1363-1380.
• Dutta, A., Kumar, S., & Basu, M. (2020). A Gated Recurrent Unit Approach To Bitcoin Price Prediction. Journal Of Risk And Financial Management, 13(2), 23.
• Ho, T. K. 1995. Random Decision Forests. In Proceedings Of 3rd International Conference On Document Analysis And Recognition, 278–282. Piscataway, NJ: IEEE.
• Hong, J., Choi, H., & Kim, W. S. (2020). A House Price Valuation Based On The Random Forest Approach: The Mass Appraisal Of Residential Property İn South Korea. International Journal Of Strategic Property Management, 24(3), 140-152.
• Jozefowicz, R., Zaremba, W., & Sutskever, I. (2015). An Empirical Exploration Of Recurrent Network Architectures. 32nd International Conference On Machine Learning, ICML 2015, 3, 2332–2340.
• Rawool, A. G., Rogye, D. V., Rane, S. G., & Bharadi, V. A. (2021). House Price Prediction Using Machine Learning. Int. J. Res. Appl. Sci. Eng. Technol, 9, 686-692.
• Saraç, H., & Hacıimamoğlu, T. U. (2018). Konut Fiyat Endeksi Verilerinin Klasik Ayrıştırma Ve Arıma Yöntemi İle Tahmin Edilmesi. Journal Of International Social Research, 11(59).
• Schonlau, M., & Zou, R. Y. (2020). The Random Forest Algorithm For Statistical Learning. Stata Journal, 20(1), 3–29. Https://Doi.Org/10.1177/1536867X20909688
• Song, H., & Choi, H. (2023). Forecasting Stock Market Indices Using The Recurrent Neural Network Based Hybrid Models: CNN-LSTM, GRU-CNN, And Ensemble Models. Applied Sciences, 13(7), 4644.
• R. Tanamal, N. Minoque, T. Wiradinata, Y. Soekamto and T. Ratih, "House price prediction model using random forest in surabaya city", TEM Journal, pp. 126-132, Feb. 2023.
• Wang, B., & Wang, J. (2021). Energy Futures Price Prediction And Evaluation Model With Deep Bidirectional Gated Recurrent Unit Neural Network And RIF-Based Algorithm. Energy, 216, 119299.
• X Chen, L. Wei, J. Xu. House Price Prediction Using LSTM. Computing Research Repository (Corr). Abs/1709.08432, September 2017