PROCENA TRŽIŠNE VREDNOSTI STANA METODOM k-NAJBLIŽIH SUSEDA

Abstract

The market value of apartments is, as the name itself suggests, defined by the sellers and the buyers through supply and demand-elements that collectively make up the market. Observing a large number of factors affecting the price of real estate is not an easy job. Price formation depends on both the characteristics of the apartment and the buyer's value-system. The basic question that a rational customer asks himself is "why would I pay a larger sum of money for the same or practically same thing than what someone else paid for it just recently?". This fact leads to the conclusion that it is necessary to know the characteristics and prices of the real estates traded in the near past and in the close surrounding. A comparative way of customer's thinking is the basic principle for defining one such model. This is a necessary but not sufficient condition. Models based on the machine learning algorithms (among them k-Nearest Neighbors algorithm) require having a larger amount of data, so that the made conclusions can be reliable, accurate, and precise.