Estimation of Housing Prices with Artificial Intelligence


Housing purchase is a multidimensional problem that requires people to meet their housing, health, safety and various socio-cultural needs with a certain budget. The developments in artificial intelligence methods now allow solutions too many problems such as buying houses in daily life. Artificial neural networks and deep learning methods are among the methods used for this purpose. In this study, an intelligent system has been developed that collects and records the housing data for sale on the internet and estimates the housing price. Housing data for sale in Istanbul was collected for the developed system. The data were divided into 10-fold cross-validation method for training and testing. The data were modeled with 14 different algorithms based on 176 attributes, and price estimation study was performed. The most successful price estimation for 852 houses in Ataşehir district of Istanbul was obtained by Random Forest Algorithm. With this study, a system has been developed in which researchers, companies operating in the housing market and consumers can estimate the housing prices. In addition, it is aimed to give researchers a new perspective for using different artificial intelligence methods or residential attributes.


Keywords


House Price Estimation, Decision Support System, Random Forest Algorithm

Author : Emrah AYDEMİR -Cemal AKTÜRK - Mehmet Ali YALÇINKAYA
Number of pages: 183-194
DOI: http://dx.doi.org/10.29228/TurkishStudies.43161
Full text:
Share:
Alıntı Yap:
Turkish Studies-Information Technologies and Applied Sciences
E-Mail Subscription

By subscribing to E-Newsletter, you can get the latest news to your e-mail.