Mitigating housing market shocks: an agent-based reinforcement learning approach with implications for real-time decision support

Research in modelling housing market dynamics using agent-based models (ABMs) has grown due to the rise of accessible individual-level data. This research involves forecasting house prices, analysing urban regeneration, and the impact of economic shocks. There is a trend towards using machine learning (ML) algorithms to enhance ABM decision-making frameworks. This study investigates exogenous shocks to the UK housing market and integrates reinforcement learning (RL) to adapt housing market dynamics in an ABM. Results show agents can learn real-time trends and make decisions to manage shocks, achieving goals like adjusting the median house price without pre-determined rules. This model is transferable to other housing markets with similar complexities. The RL agent adjusts mortgage interest rates based on market conditions. Importantly, our model shows how a central bank agent learned conservative behaviours in sensitive scenarios, aligning with a 2009 study, demonstrating emergent behavioural patterns.