Spatial Agent-Based Forecasting of Australian Housing Markets

Summary

This study presents a graph-based spatial component for a large-scale agent-based model of urban housing markets. It represents how social and economic characteristics—including fear of missing out, tendency to follow trends, and the reach of an agent's submarket activity—affect buying and selling decisions across locations. The approach aims to capture spatial relationships that may be missed by models focused on market-wide aggregates.

The model is calibrated and validated using housing data for Greater Sydney. Its simulations produce forecasts for the overall market and for local government areas, with outcomes emerging from individual agent decisions. They also reveal modeled differences in submarket preferences among first-time buyers, investors, and local and overseas investors. The description does not give forecast-error measures, a comparison with other forecasting methods, or evidence from regions outside Sydney. The reported outputs therefore show the model's scope and behavioral detail, while its predictive value beyond the stated setting remains unclear.

Key ideas

• A graph-based structure incorporates spatial relationships into an urban housing agent-based model.
• Agent decisions reflect social and economic factors such as trend following and fear of missing out.
• The Sydney application produces both market-wide and local government area forecasts.
• Simulations distinguish modeled preferences across buyer and investor groups, though the description gives no forecast accuracy results.

Tags

# The impact of social influence in Australian real-estate: market forecasting with a spatial agent-based model


# The impact of social influence in Australian real-estate: market forecasting with a spatial agent-based model









Housing markets are inherently spatial, yet many existing models fail to capture this spatial dimension. Here we introduce a new graph-based approach for incorporating a spatial component in a large-scale urban housing agent-based model (ABM). The model explicitly captures several social and economic factors that influence the agents' decision-making behaviour (such as fear of missing out, their trend following aptitude, and the strength of their submarket outreach), and interprets these factors in spatial terms. The proposed model is calibrated and validated with the housing market data for the Greater Sydney region. The ABM simulation results not only include predictions for the overall market, but also produce area-specific forecasting at the level of local government areas within Sydney as arising from individual buy and sell decisions. In addition, the simulation results elucidate agent preferences in submarkets, highlighting differences in agent behaviour, for example, between first-time home buyers and investors, and between both local and overseas investors.

Shown in full with attribution under the source's licence. Licence: abstract CC0

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.