Multiedge Graph Convolutional Network for House Price Prediction

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. In the context of construction management and property valuation, the multiedge GCN model introduces an enhanced level of reliability for house price prediction. It stands out with its improved interpretability, rooted in its ability to maintain the inherent structure of the house price data set. This added transparency provides professionals with a more profound understanding and trust in prediction outcomes. By encompassing the richer content of the house price data set that includes the multidependency information, the model presents a comprehensive view of house price data sets, facilitating a more accurate and thorough understanding of housing market patterns. As a result, the GCN model matches the accuracy of other ML models while providing greater interpretability and transparency. This model’s capabilities are expected to arm investors, contractors, and policymakers with valuable insights, aiding informed decision-making. It is also envisaged as a beneficial tool for construction project owners and contractors in refining budgets and informed investment decisions. The synthesis of transparency, representativeness, and accuracy makes this model a dependable tool for construction managers to make informed decisions, ultimately enhancing their operational efficacy.