期刊名称：Journal of Statistical and Econometric Methods
印刷版ISSN：2241-0384
电子版ISSN：2241-0376
出版年度：2020
卷号：9
期号：4
页码：31-38
语种：English
出版社：Scienpress Ltd
摘要：Housingprices are an important reflection of the economy, and housing price ranges areof great interest for both buyers and sellers. The goal of this paper is toempirically conduct the best machine learning regression model for TurkishHousing Market by comparing accuracy scores and absolute deviations of testresults by using Python programming language and Keras library for thefive-year period from January 2015 to December 2019. This study consists of 15explanatory variables describing (almost) every aspect of houses in Istanbul,Izmir and Ankara. These fifteen explanatory building and dwelling variables areused for each prediction model. In this study, three different data models arecreated by using support vector machine, feedforward neural networks andgeneralized regression neural networks algorithms. The experiments demonstrate thatthe Feedforward Neural Network model, based on accuracy, consistentlyoutperforms the other models in the performance of housing price prediction.According to another result of the study, the most important variables in themodel are the location of the house and the size of the house, while the sizeof the terrace is determined as the least important variable.
关键词：Housing market; Zingat.com; Machinelearning; House price prediction; Python programming language; Keras library.
