Abstract
The real estate sector is evolving and changing rapidly with the
increase in housing demand, and new luxury housing projects appear every
day. The reliability of housing market investments is largely dependent
on accurate pricing. The aim of this study is to introduce a dynamic
pricing procedure that estimates housing prices using the most important
attributes of a house. To this end, a hybrid modeling system is proposed
employing linear regression, clustering analysis, nearest neighborhood
classification, and the Support Vector Regression (SVR) method. The
housing data of the Kadikoy area in Istanbul, collected via manual web
scraping, was used for the raining and validation of the proposed
algorithm. The results of the hybrid model were compared using multiple
linear regression, ridge regression, and Support Vector Machines (SVMs).
The experimental results show that the proposed model is superior, both
in terms of Residual Mean Square Error (RMSE) and Mean Absolute
Percentage Error (MAPE) measures. Therefore, the proposed dynamic hybrid
modelling structure can be successfully used for predicting house
pricing.