Year of Graduation
Correlation of Real Estate Prices in Characteristics Space
In this paper, we study the choice of the metric corresponding to the proximity of the real estate objects in Perm. Data is taken from the advertisement website “Metrosphera” for the period from October 2014 to February 2015. To set the apartment price the seller always focuses on internal characteristics of an apartment, such as residential area or the number of rooms, house characteristics, such as the number of floors of the house or construction material, and external characteristics including quality and accessibility of schools, distance to a city center or crime rate. To adjust the price the seller focuses not only on the observed and unobserved factors of the apartment, house and its environment but also on the prices of analogs marketed objects. Analogs can be selected both by geographic proximity or by characteristics similarity. In this paper, we use ensemble clustering approach and spatial lag model to measure objects proximity and test that the proximity of objects in the characteristics space along with spatial correlation explains the significant variation in price.