We propose a novel and intuitive risk-neutral valuation model for real estate derivatives. We first model the underlying efficient market price of real estate and then construct the observed index value with an adaptation of the price update rule by Blundell and Ward (1987). The resulting index...

This paper proposes a methodology for using machine learning regression models to create price indices. In our study we developed six commercial real estate price indeces for the city of New York from year 2000 to 2019. The regression models used in this study are eXtreme Gradient Boosting Tree...

We propose a new and intuitive risk-neutral valuation model for real estate derivatives which are linked to autocorrelated indices. We model the observed index with an autoregressive model which can be estimated using standard econometric techniques. The resulting index behavior can easily be...