This paper aims to test the hedging ability of housing investment against inflation in Japan and the USA during the period 2000–2020.
This study applies the deep learning method and The exponential general autoregressive conditional heteroskedasticity in mean (1, 1) model with breaks.
Within the asymmetric framework, it is found that housing returns (HR) can hedge against inflation in both these markets, which mentions that when investing in the housing market in Japan and the USA, investors are compensated for bearing from inflation. This result is consistent with Fisher’s hypothesis. Especially, the empirical results show that the risk-return tradeoff is available in Japan’s housing market and not available in the US housing market. Any signal of a high inflation rate – referred to as “bad news” – may cause a drop in HR in Japan and a raise in the USA.
To the best of the author’s knowledge, this is one of the first studies using the deep learning method (long short-term memory model) to estimate the expected/unexpected inflation rates.
