Machine Learning Applications to Land and Structure Valuation - New Publication by Martin Hoesli
In some applications of supervised machine learning, it is desirable to trade model complexity with greater interpretability for some covariates while letting other covariates remain a “black box”. An important example is hedonic property valuation modeling, where machine learning techniques typically improve predictive accuracy, but are too opaque for some practical applications that require greater interpretability. This problem can be resolved by certain structured additive regression (STAR) models, which are a rich class of regression models that include the generalized linear model (GLM) and the generalized additive model (GAM). Typically, STAR models are fitted by penalized least-squares approaches.
In a new study, GFRI's Professor Martin Hoesli and his co-authors explain how one can benefit from the excellent predictive capabilities of two advanced machine learning techniques: deep learning and gradient boosting. Furthermore, they show how STAR models can be used for supervised dimension reduction and explain under what circumstances their covariate effects can be described in a transparent way. They apply the methodology to residential land and structure valuation, with very encouraging results regarding both interpretability and predictive performance.
The paper was co-authored with Michael Mayer, Steven C. Bourassa, and Donato Scognamiglio. It is forthcoming in the Journal of Risk and Financial Management, and can be found here.
Apr 20, 2022