Please use this identifier to cite or link to this item: http://hdl.handle.net/10609/148363
Title: Predicción del valor de mercado de una vivienda en la ciudad de Barcelona mediante la obtención de un conjunto de datos y el desarrollo de un algoritmo de aprendizaje automático
Author: Miravé Carreño, Miguel Ángel
Tutor: Andrés Sanz, Humberto
Abstract: The purpose of this project is to obtain a tool that allows predicting the market value of a residential property in the city of Barcelona by obtaining a dataset and using a machine learning model. Various analyses are conducted to identify the attributes of properties that determine their price, the optimal data source and extraction method, and the suitable machine learning model for predicting housing prices. The dataset is obtained from the real estate portal Idealista using a web scraper tool. The dataset is processed and analyzed before being provided to an XGBoost machine learning algorithm, which is developed, optimized, and evaluated. The fitting metric obtained is the relative mean absolute error, with a value of 15%. The model's fit is considered satisfactory comparatively, being similar to that of official appraisers and substantially lower than that of free online appraisers. A graphical interface is developed, allowing users to obtain a prediction of the property value based on the attributes inputted.
Keywords: web scraping
Document type: info:eu-repo/semantics/bachelorThesis
Issue Date: Jun-2023
Publication license: http://creativecommons.org/licenses/by-nc-nd/3.0/es/  
Appears in Collections:Bachelor thesis, research projects, etc.

Files in This Item:
File Description SizeFormat 
miravecaTFG0623memoria.pdfMemoria del TFG2,27 MBAdobe PDFThumbnail
View/Open
Share:
Export:
View statistics

This item is licensed under aCreative Commons License Creative Commons