Predviđanje cijena najma nekretnina na Airbnb platformi pomoću strojnog učenja

master's thesis

• Title (english): Predicting Real Estate Rental on the Airbnb Platform Using Machine Learning
• Author: Jakov Viktor Munjiza
• Mentor: Marin Šilić (mentor)
• Committee member: Marin Šilić (predsjednik povjerenstva)
• Committee member: Goran Delač (član povjerenstva)
• Committee member: Klemo Vladimir (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2022-07-01, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Airbnb je općepoznata platforma za iznajmljivanje smještaja koja omogućava lakše posredovanje između pružatelja usluge i korisnika. Glavna premisa ovog diplomskog rada zasniva se na analizi skupa podatka i razvijanju modela za predikciju cijena u svrhu indikacije novim korisnicima platforme radi poboljšanja profita. Iako Airbnb te druge slične stranice svojim pružateljima usluga omogućavaju približnu procjenu cijene opisanog objekta, i dalje ne postoji besplatna i prvenstveno točna internetska usluga koja bi pomogla iznajmljivačima u maksimizaciji svoje dobiti. Kako je osnovna procjena uzimala u obzir specifikacije unesenog objekta te je djelomično uvažavala trendove lokalnog tržišta, osmišljen je web sustav koji se pokazao uspješnim za korisnike i pružatelje usluga.

Abstract (english)

Airbnb is a well-known accommodation rental platform that enables intermediation between service providers and users. The main premise of this work is based on the analysis of datasets and the development of a price forecasting model to provide guidance to new users of the platform to improve profits and revenues. Although Airbnb and other similar websites allow their service providers to estimate the price of the described facility. The basic valuation considers the specifications of the entered property and, to some extent local market trends, but there is still no free and, above all, accurate Internet service that helps landlords maximize their profits. The web service was realized as an application of the developed model with the intention to allow service providers to maximize their profits in a simple and intuitive way.

• Keywords: strojno učenje; model; predviđanje; cijene; Airbnb; web sustav; maksimizacija; analiza skupa podataka; profit
• Keywords (english): machine learning; model; forecasting; prices; Airbnb; web service; maximization; statistical data analysis; profit
• Language: croatian
• URN:NBN: urn:nbn:hr:168:272842
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-13 15:41:20