USING ARTIFICIAL NEURAL NETWORK METHOD TO PREDICT HOUSING PRICES

Yıl 2018, Sayı: 20, 285 - 300, 31.01.2018

Özgür Yılmazel , Aslı Afşar , Sibel Yılmazel

https://doi.org/10.18092/ulikidince.341584

Cited By: 15

Öz

With improvements in technology
artificial neural network has been added among the methods for house price
prediction. This study explores the usage of artificial neural network method
to predict the housing prices in the city of Eskişehir. The physical characteristics
of housing such as the size of the apartment, number of the rooms, if the
apartment is located on the first floor or not, the number of the floors of the
building, whether it has central heating, number of the bathrooms, whether
there is an elevator, and parking lot of the building, if there is built-in
kitchen cabinets, availability of fiber internet connection in the building,
the neighborhood of the apartment and the distance to the nearest tram stop are
used within the neural network model. Different numbers of neurons are tried
out within the generated neural network. The results are compared and in
conclusion it was shown that artificial neural network is an effective method
to predict the housing prices.

Anahtar Kelimeler

Housing Sales Price, Artificial Neural Network, ANN, Housing Market in Eskisehir

KONUT FİYAT TAHMİNİNDE YAPAY SİNİR AĞLARI YÖNTEMİNİN KULLANILMASI

Öz

Teknolojinin
gelişmesiyle konut fiyat tahmini için kullanılan yöntemlere yapay sinir ağları yöntemi
de eklenmiştir. Bu çalışmada Eskişehir ilinde satılık konut fiyatlarının
tahmininde yapay sinir ağlarının kullanılması araştırılmıştır. Konutların
büyüklüğü, oda sayısı, birinci katta bulunup bulunmadığı, konutun bulunduğu
binadaki toplam kat sayısı, merkezi ısıtmalı olup olmadığı, banyo sayısı,
asansörün, otoparkın, ankastre mutfağın ve fiber internet bağlantısının bulunup
bulunmadığı gibi farklı fiziksel özellikleri, bulunduğu mahalle ve tramvaya
uzaklığı parametreleri ile yapay sinir ağları modelleri kurulmuştur.
Geliştirilen yapay sinir ağları modellerinde gizli katman nöron sayıları
farklılaştırılarak 19 adet model elde edilmiş ve bu modellerin
performanslarının karşılaştırması yapılarak en uygun gizli katman nöron sayısı
belirlenmiştir. Sonuç olarak yapay sinir ağlarının konut fiyatının tahmin edilmesinde
etkili bir araç olduğu gösterilmiştir.

Anahtar Kelimeler

Konut Satış Fiyatı, Yapay Sinir Ağları, YSA, Eskişehir'de Konut Piyasası

Kaynakça

• Abidoye, R. B. and Chan, A. P. C. 2017. Modeling Property Values in Nigeria Using Artificial Neural Network. Journal of Property Research. 1-18.
• Abraham, M. 2016. Determinants of Residential Property Value in New Zeland: A Neural Network Approach, Department of Applied Business, New Zealand Government Institute of Technology (Whitireia). Auckland. 1-24.
• Akel, V. Ve Bayramoğlu, M. F. 2008. Kriz Dönemlerinde Yapay Sinir Ağları İle Finansal Öngörüde Bulunma: İMKB 100 Endeksi Örneği. In International Symposium on International Capital Flows and Emerging Markets. 24-28.
• Akgül, I. 2003. Zaman Serilerinin Analizi ve ARIMA Modelleri. Der Yayınları. İstanbul. Borst, R.A. 1991. Artificial Neural Networks: The Next Modelling/Calibration Technology For The Assessment Community. Artificial Neural Networks, s. 69‐94.
• Cechin, A., Antonio, S. And Gonzales, M. A. 2000. Real Estate Value at Porto Alegre City Using Artificial Neural Networks. Neural Networks, Proceedings, Sixth Brazilian Symposium on IEEE, November 2000. 237-242.
• Coakley, J. R. and Brown, C. 2000. Artificial Neural Networks in Accounting and Finance: Modelling Issues, International Journal of Intelligent Systems in Accounting. Finance and Management. 9 (2), 119-144.
• Do, A. Q. and Grudnitski, G. 1992. A neural network approach to residential property appraisal. The Real Estate Appraiser. 58 (3). 38-45.
• Ecer, F. 2014. Türkiye’deki Konut Fiyatlarının Tahmininde Hedonik Regresyon Yöntemi ile Yapay Sinir Ağlarının Karşılaştırılması. International Conference On Eurasian Economies. 1-10.
• Eibe, F., Mark, A., Hall, and Ian H. Witten (2016). The WEKA Workbench. Online Appendix for Data Mining: Practical Machine Learning Tools and Techniques. Morgan Kaufmann, Fourth Edition.
• Elmas, Ç. 2003. Yapay Sinir Ağları, Birinci Baskı, Ankara: Seçkin Yayıncılık.
• Esperanzo, M. and Gallego, J. 2004. Artificial Intelligence Applied to Real Estate Valuation an Example fort he Appraisal of Madrid. Catastro. April 2004. 255-265.
• Hagan, M. T., Demuth, H. B. and Beale, M. H. 1996. Neural Network Design. PWS Pub. Co.. Boston. 6.
• Haykin, S. and Network, N. 2004. A Comprehensive Foundation. Neural Networks. New York: MacMillan College Publishing Company. 246-262.
• Limsombunchai, V., Gan, C. and Lee, M. 2004. House Price Predicting Using Artificial Neural Networks: A Comparative Study with Hedonic Price Model. American Journal of Applied Sciences. 1 (3). 193-201.
• Khalafallah, A. 2008. Neural Networks Based Model for Predicting Housing Market Performance. Tsinghua Science & Technology. 13, 325-328.
• Mimis, A., Rovolis, A. and Stamou, M. 2013. Property Valuation with Artificial Neural Network: The Case of Athens. Journal of Property Research. 30 (2). 128-143.
• Nghiep, N. and Cripps, A. 2001. Predicting Housing Value: A Comparison of Multiple Regression Analysis and Artificial Neural Networks. Journal of Real Estate Research. 22(3). 313-336.
• Özkan, G., Yalpır, Ş. ve Uygunol, O. 2007. An Investigation on the Price Estimation of Residable Real Estates by Using ANN and Regression Methods. The 12th Applied Stochastic Models and Data Analysis International Conference (ASMDA). Chania, Crete, Greece.
• Rossini, P. A. 1997. Artificial Neural Networks Versus Multiple Regression in the Valuation of Residential Property. Australian Land Economics Review. 3 (1). 1-12.
• Selim, H. 2009. Determinants of House Prices in Turkey: Hedonic Regression Versus Artificial Neural Network. Expert Systems with Applications. 36 (2). 2843–2852.
• Selim, S. ve Demirbilek, A. 2009. Türkiye’de Konutların Kira Değerinin Analizi: Hedonik Model ve Yapay Sinir Ağları Yaklaşımı. Aksaray Üniversitesi İİBF Dergisi. Ocak 2009, 1 (1). 73-90.
• Worzala, E., Lenk, M. and Silva, A. 1995. An Exploration of Neural Networks and Its Application to Real Estate Valuation. Journal of Real Estate Research. 10 (2). 185-201.
• Yıldız, B. 2009. Finansal Analizde Yapay Zeka, Detay Yayıncılık, Ankara, 10.
• Zurada, J. M., Levitan, A. S., and Guan, J. 2011. Non-Conventional Approaches to Property Value Assessment. Journal of Applied Business Research, 22 (3). 1-14.