Treffer: EVALUATION OF REAL ESTATE MARKET VALUE IN UKRAINE USING WEB-SCRAPING.

Market value is one of the most important kind of information for every type of business – for startups on the planning stage, as well as for already grown business. It allows to make more accurate revenue predictions at financial planning stage and therefore investment decisions. In some cases, identification of market value can be a trivial task, when, for example, we deal with open organized information, but mostly, estimation of this parameter is very complex task that can be time consuming and requires the involvement of experts in various areas. It becomes even more difficult while trying to estimate the value of illiquid assets such as assets on real estate markets. The objective of the paper is the estimation the real estate market value using the approach of extracting and structuring data from web-sources and available data by web scraping based on Python programming language. Web crawler is more advanced software, it is the artificial intelligence that can navigate the web sites, follow the search links and extract data using specific rules. As the data source, ria.ua web site is chosen. The total market value, according to information represented on ria.ua is approximately $ 10,9 billion. The evaluation shows the concentration of market mostly in Kiev, except business property, country houses, hotels, land and warehouses. At the same time, Kiev is the leader in the sphere of office complexes, parking places, recreation. The leaders of apartment sales are Kiev and Odesa regions, other regions are significantly behind Kiev and Odesa. On the basis of carried out analysis, we can come to the conclusion that the price is highly correlated with the type of real estate and moderately correlated with region of sale. [ABSTRACT FROM AUTHOR]

Copyright of Galician economic journal is the property of Ternopil Ivan Puluj National Technical University and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)