Multiedge Graph Convolutional Network for House Price Prediction

Fatemeh Mostofi, Vedat Toǧan*, Hasan Basri Başaǧa, Ahmet Çltlpltloǧlu, Onur Behzat Tokdemir

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

3 Citations (Scopus)

Abstract

Accurate house price prediction allows construction investors to make informed decisions about the housing market and understand the growth opportunities for development and the risks and rewards of different construction projects. Machine learning (ML) models have been utilized as house price predictors, reducing decision-making costs, and increasing reliability. To further improve the reliability of the existing predictors, this study develops a hybrid multiedge graph convolutional network (GCN) that considers the various relationships between house price records. The developed hybrid multiedge GCN receives richer input from the multidependency information and thus provides a more reliable prediction that accounts for price changes based on the neighborhood, building age, and number of bedrooms. Compared to other ML approaches, the developed multiedge GCN house price predictor displayed good prediction accuracy while providing valuable insights into the factors that affect the house price, such as the desirability of different neighborhoods and building age.

Original languageEnglish
Article number04023112
JournalJournal of Construction Engineering and Management - ASCE
Volume149
Issue number11
DOIs
Publication statusPublished - 1 Nov 2023

Bibliographical note

Publisher Copyright:
© 2023 American Society of Civil Engineers.

Keywords

  • Construction cost management
  • Graph convolutional network (GCN)
  • House price prediction
  • Informed decision-making
  • Multiedge graph

Fingerprint

Dive into the research topics of 'Multiedge Graph Convolutional Network for House Price Prediction'. Together they form a unique fingerprint.

Cite this