Multiedge Graph Convolutional Network for House Price Prediction

Mostofi F., TOĞAN V., BAŞAĞA H. B., Çltlpltloǧlu A., Tokdemir O. B.

Journal of Construction Engineering and Management, cilt.149, sa.11, 2023 (SCI-Expanded) identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 149 Sayı: 11
  • Basım Tarihi: 2023
  • Doi Numarası: 10.1061/jcemd4.coeng-13559
  • Dergi Adı: Journal of Construction Engineering and Management
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, Aerospace Database, Applied Science & Technology Source, Business Source Elite, Business Source Premier, Communication Abstracts, Compendex, Computer & Applied Sciences, ICONDA Bibliographic, INSPEC, Metadex, Public Affairs Index, DIALNET, Civil Engineering Abstracts
  • Anahtar Kelimeler: Construction cost management, Graph convolutional network (GCN), House price prediction, Informed decision-making, Multiedge graph
  • İstanbul Teknik Üniversitesi Adresli: Evet

Özet

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.