Genetic algorithm application for real estate market analysis in the uncertainty conditions

Abstract

Every real estate investment decision making, because of the high capital-intensive character of properties, requires careful analysis of information. Availability of the information, market specifcity and unpredictable or sudden changes on it cause that all real estate investments are subject to considerable risk and uncertainty. This specifcity causes that, one can never be sure, that the collected set of information is complete though reliable for decision inference. The process of property market information collection, from numerical point of view is infnite since the information can be continuously supplemented or clarifed. That is the reason for alternative to commonly (classically) used methods search that are efective in the selection of closest solutions optimal for multidimensional real functions, taking into account the global maximum. The paper attempts to decrease the impact of the factors that cause uncertainty on the quality of real estate investment decisions through the tools based on the simulation of the process of natural selection and biological evolution application proposal. The aim of the study is to analyse the potential of the methodology based on genetic algorithms (GA) as part of the automated valuation models component in the uncertainty conditions and support investment decisions on the real estate market. The developed hybrid model (based on genetic algorithm and Hellwig’s method compound) allows to select properties adequate to the adopted assumptions, i.e. individuals best suited to the environment. The tool can be used by real estate investment advisors and potential investors.