A machine learning exploration of real estate market dynamics
With a total net worth approaching £10 trillion, and housing stock itself worth over £7 trillion, there is clearly a close relationship between the wider economy and the real estate market in the UK. As a significant component of national wealth, changes in the property market have a direct and major impact on the economy.
The importance of the housing market to the wider economy, necessitates accurate, stable and robust forecasting. The application of machine learning methodologies to real estate forecasting is a developing trend, and can be attributed both to the increased availability of big data, and the ability of machine learning techniques to deal with the nonlinearity that is often present within time-series data.
My research will focus on the application of machine learning to explore various dynamics within the real estate market, such as locational volatility, sentiment analysis of volatility, and the susceptibility of the market to boom and bust phenomena. This particular approach will enable a deeper exploration of these dynamics, due to the ability of machine learning techniques to more efficiently analyse big data.