A Novel Machine Learning Model for Estimation of Sale Prices of Real Estate Units

TLDR

Predicting the price of housing is of paramount importance for near‑term economic forecasting of any nation. The paper proposes a novel model that estimates new housing prices at design or construction start using a deep belief restricted Boltzmann machine combined with a unique non‑mating genetic algorithm. The model employs a data structure that incorporates many economic variables and their time‑dependent and seasonal variations, applies dimensionality‑reduction strategies to enable computation on standard workstations, and is built upon the deep belief restricted Boltzmann machine and non‑mating genetic algorithm. The model enables construction firms to assess market viability before building and has been shown to be effective and accurate in a case study.

Abstract

Predicting the price of housing is of paramount importance for near-term economic forecasting of any nation. This paper presents a novel and comprehensive model for estimating the price of new housing in any given city at the design phase or beginning of the construction through ingenious integration of a deep belief restricted Boltzmann machine and a unique nonmating genetic algorithm. The model can be used by construction companies to gauge the sale market before they start a new construction and consider to build or not to build. An effective data structure is presented that takes into account a large number of economic variables/indices. The model incorporates time-dependent and seasonal variations of the variables. Clever stratagems have been developed to overcome the dimensionality curse and make the solution of the problem amenable on standard workstations. A case study is presented to demonstrate the effectiveness and accuracy of the model.