Konut değerlemede uzman görüşü ve yapay sinir ağı ile modellemelerin karşılaştırılması

Yıl 2024, , 43 - 47, 26.02.2024

Şükran Yalpır , Erol Yalpır

https://doi.org/10.51765/tayod.1421771

Öz

Bu çalışmada Ankara ili, Yenimahalle ilçesi, Batıkent Bölgesi sınırları içerisinde bulunan konutların öznitelik verileri ve coğrafi konumlarının taşınmaz değerine olan etkileri incelenmiştir. Veri seti düzenlenirken Coğrafi Bilgi Sistemlerinden faydalanılmıştır. Çalışma kapsamında nominal değerleme ve Yapay sinir ağları (YSA) modellemede kullanılmıştır. Bölgedeki taşınmazların elde edilebilecek en yüksek hassasiyet ve en yüksek doğrulukta taşınmaz değer haritaları oluşturularak değer tespitleri yapılmıştır. Modellemede Nominal ve YSA yöntemlerine göre R2 değeri sırayla 0,76 ve 0,89 olarak bulunmuştur. YSA ile daha başarılı piyasa sonuçları tahmin edilmiştir. Nominal değerlemede ise uzman görüşü ile oluşan matematiksel modelin piyasa değerini tahmininin göz ardı edilemeyecek başarı elde ettiğini ve gelecekte modelin güncellemelerle sürdürülebilir olduğu gözlemlenmiştir.

Anahtar Kelimeler

Konut Değer Tahmini, Nominal Modelleme, Yapay Sinir Ağları, CBS, Tahmin

Comparison of artificial neural networks and multiple regression analysis methods in housing valuation estimation: the example of Yenimahalle/Ankara)

Öz

Due to the involvement of numerous factors in determining the sale prices of residential properties, accurately predicting market values is a critical issue. This research study aims to compare the results of models created using both a statistical method, Multiple Regression Analysis (MRA), and one of the artificial intelligence techniques, Artificial Neural Networks (ANN), for the rapid and accurate prediction of market values, which are determined based on multiple variables for residential properties. Within the scope of this study, real estate listings for sale in different neighborhoods of Yenimahalle, Ankara, were examined. These listings were collected from an e-commerce website in Turkey, comprising a total of 220 residential properties for sale. Nine parameters that have the most significant impact on determining a property's market value were selected, and MRA and ANN models were developed. When the data were examined, it was seen that the selected ANN method gave more successful results in terms of regression and accuracy rate than MRA.

Anahtar Kelimeler

Housing Price, Nominal Valuation, Artificial Neural Networks, GIS, Prediction

Kaynakça

• Abidoye, R. B., Chan, A. P. C. (2017). Modelling property values in Nigeria using artificial neural network. Journal of Property Research, 34(1), 36–53. https://doi.org/10.1080/09599916.2017.1286366
• Agatonovic-Kustrin, S., & Beresford, R. (2000). Basic concepts of artificial neural network (YSA) modeling and its application in pharmaceutical research. Journal of pharmaceutical and biomedical analysis, 22(5), 717-727. https://doi.org/10.1016/S0731-7085(99)00272-1
• Ayalke, Z., & Sisman, A. (2022). Nominal land valuation with Best-Worst method using Geographic Information System: A case of Atakum, Samsun. ISPRS International Journal of Geo-Information, 11(4), 213. https://doi.org/10.3390/ijgi11040213
• Dongare, A. D., Kharde, R. R., & Kachare, A. D. (2012). Introduction to artificial neural network. International Journal of Engineering and Innovative Technology (IJEIT), 2(1), 189-194.
• Garcia, N., Gamez, M., & Alfaro, E. (2008). ANN+ GIS: An automated system for property valuation. Neurocomputing, 71, 733–742. https://doi.org/10.1016/j.neucom.2007.07.031
• IAAO. (2017). Standard on mass appraisal of real prop. IAAO.
• Lee, C. (2021). Enhancing the performance of a neural network with entity embeddings: an application to real estate valuation. Journal of Housing and the Built Environment, 1–16. https://doi.org/10.1007/s10901-021-09885-2
• Mancia, A., Droj, G., & Droj, L. (2010). Nominal assets valuation by GIS. GIS OPEN, 1-6.
• Mete, M. O., & Yomralioglu, T. (2019). Creation of nominal asset value-based maps using GIS: A case study of Istanbul Beyoglu and Gaziosmanpasa districts, GI_Forum, 7(2), 98–112. https://doi.org/10.1553/giscience2019_02_s98
• Mete, M. O., & Yomralioglu, T. (2022). Mass valuation of Real Estate Using GIS-based nominal valuation and machine learning methods. 28th YSAual Conference of the European Real Estate Society (ERES), Milan, Italy, 22-25.
• Mimis, A., Rovolis, A., & Stamou, M. (2013). Property valuation with artificial neural network: The case of Athens. Journal of Property Research, 30(2), 128-143. https://doi.org/10.1080/09599916.2012.75555
• Morillo Balsera, M. C., Martinez-Cuevas, S., Molina Sanchez, I., Garcia-Aranda, C., & Martinez Izquierdo, M. E. (2018). Artificial neural networks and geostatistical models for housing valuations in urban residential areas. eografisk Tidsskrift-Danish Journal of Geography, 118(2), 118, 184–193. https://doi.org/10.1080/00167223.2018.1498364
• Ögücü, M. O. (2006). Yapay sinir ağları ile sistem tanıma, (Yayın No. 223555), [Yüksek Lisans tezi, İstanbul Teknik Üniversitesi], YÖK Ulusal tez Merkezi.
• Pagourtzi, E., Assimakopoulos, V., Hatzichristos, T., & French, N. (2003). Real estate appraisal: a review of valuation methods. Journal of Property Investment & Finance, 21(4), pp. 383–401. https://doi.org/10.1108/14635780310483656
• Renigier-Biłozor, M., Źróbek, S., Walacik, M., Borst, R., Grover, R., & D’Amato, M. (2022). International acceptance of automated modern tools use must-have for sustainable real estate market development. Land Use Policy, 113, 105876. https://doi.org/10.1016/j.landusepol.2021.105876
• Selim, H. (2009). Determinants of house prices in Turkey: Hedonic regression versus artificial neural network. Expert systems with Applications, 36(2), 2843–2852. https://doi.org/10.1016/j.eswa.2008.01.044
• Unel, F. B., & Yalpir, S. (2023). Sustainable tax system design for use of mass real estate appraisal in land management. Land Use Policy, 131, 106734. https://doi.org/10.1016/j.landusepol.2023.106734
• Utkucu, T. (2010). Gayrimenkul değerlemesi ve hazine taşınmazlarının türkiye ekonomisine etkisi, Nobel Kitabevi.
• Wang, D., & Li, V. J. (2019). Mass appraisal models of real estate in the 21st Century: A systematic literature review. Sustainability, 11(24), 7006. https://doi.org/10.3390/su11247006
• Yomralioglu, T. (1993). A nominal asset value-based approach for land readjustment and ıts ımplementation using geographical ınformation systems [PhD thesis, University of Newcastle upon Tyne]. https://web.itu.edu.tr/tahsin/PAPERBOX/T01.pdf
• Zhou, G., Ji, Y., Chen, X., & Zhang, F. (2018). Artificial neural networks and the mass appraisal of real estate. International Journal of Online and Biomedical Engineering, 14, 180–187. https://doi.org/10.3991/ijoe.v14i03.8420