A multi-level modeling approach for predicting real-estate dynamics

Purpose This research developed a model to understand and predict housing market dynamics and evaluate the significance of house permits data in the model’s forecasting capability. Design/methodology/approach The research uses a multilevel algorithm consisting of a machine-learning regression model to predict the independent variables and another regressor to predict the dependent variable using the forecasted independent variables. Findings The research establishes a statistically significant relationship between housing permits and house prices. The novel approach discussed in this paper has significantly higher prediction capabilities than a traditional regression model in forecasting monthly average prices (R-squared value: 0.5993), house price index prices (R-squared value: 0.99) and house sales prices (R-squared value: 0.7839). Research limitations/implications The impact of supply, demand and socioeconomic factors will differ in various regions. The forecasting capability and significance of the independent variables can vary, but the methodology can still be applicable when provided with the considered variables in the model. Practical implications The resulting model is helpful in the decision-making process for investments, house purchases and construction as the housing demand increases across various cities. The methodology can benefit multiple players, including the government, real estate investors, homebuyers and construction companies. Originality/value Existing algorithms and models do not consider the number of new house constructions, monthly sales and inventory in the real estate market, especially in the United States. This research aims to address these shortcomings using current socioeconomic indicators, permits, monthly real estate data and population information to predict house prices and inventory.