Sustav za procjenu nekretnina na temelju javno dostupnih podataka ponude

undergraduate thesis

• Title (english): System for real estate evaluation based on public available offering data
• Author: Mislav Jakšić
• Mentor: Zdravko Galić (mentor)
• Committee member: Zdravko Galić (predsjednik povjerenstva)
• Committee member: Slaven Zakošek (član povjerenstva)
• Committee member: Boris Milašinović (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2017-02-24, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Razvijen je sustav za procjenu nekretnina na temelju javno dostupnih podataka ponude nekretnina. Sustav se sastoji od tri zavisna dijela: sakupljača podataka, baze podataka i programa za procjenu nekretnina. Sakupljač podataka traži, preuzima i iz web stranica prikuplja podatke o nekretninama. Prikupljeni podatci pohranjuju se u bazu podataka kako bi se lakše obradili. Program za procjenu gradi modele za procjenu nekretnina koristeći algoritme linearne regresije i "gradient booster tree" na temelju prikupljenih podataka. Rezultati pokazuju kako je moguće brzo i točno procijeniti nepoznate nekretnine koristeći javno dostupne podatke.

Abstract (english)

A system for real estate valuation has been developed. It is comprised of three dependant parts: a web scraper, a database and a real estate valuation program. The web scraper searches for, downloads and extracts real estate data from web pages. The extracted data is stored in a database, so it can be analyses more easily. The real estate valuation program builds a valuation model using linear regression and gradient booster tree algorithms based on the extracted real estate data. The results show that it is possible to valuate unknown real estate based on the publicly available real estate data.

• Keywords: Procjena nekretnina; Prikupljanje podataka; Strojno učenje; Linearna regresija; Gradient booster tree
• Keywords (english): Real estate valuation; Web scraping; Machine learning; Linear regression; Gradient booster tree
• Language: croatian
• URN:NBN: urn:nbn:hr:168:664106
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2019-03-13 21:07:51