Publicação
Forecasting models for real estate market analysis The case study of Portugal
| datacite.subject.fos | Ciências Naturais::Ciências da Computação e da Informação | pt_PT |
| dc.contributor.advisor | Neto, Miguel de Castro Simões Ferreira | |
| dc.contributor.advisor | Jardim, João Bruno Morais de Sousa | |
| dc.contributor.author | Coutinho, Ana Lúcia Barata | |
| dc.date.accessioned | 2024-03-26T12:09:05Z | |
| dc.date.available | 2024-03-26T12:09:05Z | |
| dc.date.issued | 2024-02-05 | |
| dc.description | Project Work presented as the partial requirement for obtaining a Master's degree in Information Management, specialization in Knowledge Management and Business Intelligence | pt_PT |
| dc.description.abstract | The real estate market is known for its difficulties and volatility, particularly in determining property values, which significantly impact economic choices and societal well-being. Accurate predictions of property prices can facilitate informed decision-making and influence investment strategies and market dynamics. This study focuses on predicting property prices in Portugal and looks at different regions with a focus on Lisbon. It attempts to use innovative methods such as Decision Tree, Random Forest, Artificial Neural Networks, Linear Regression, and K-Nearest Neighbors. The research provides an in-depth evaluation of forecasting techniques by analyzing historical data and employing various machine learning algorithms. The models are specifically designed to understand the complex dynamics of different property types in different regions of Portugal. Overall, the Random Forest model is the best model for predicting property prices, followed by Decision Tree model. This forecast is also important because it provides us with an insight into the importance of certain features in real estate property prices. Using advanced predictive models does not only enhance the understanding of real estate market trends but also enables stakeholders to make informed decisions. | pt_PT |
| dc.identifier.tid | 203563751 | pt_PT |
| dc.identifier.uri | http://hdl.handle.net/10362/165446 | |
| dc.language.iso | eng | pt_PT |
| dc.rights.uri | http://creativecommons.org/licenses/by/4.0/ | pt_PT |
| dc.subject | Real Estate | pt_PT |
| dc.subject | Real Estate Property Prices | pt_PT |
| dc.subject | Machine Learning | pt_PT |
| dc.subject | Random Forest | pt_PT |
| dc.subject | Artificial Neural Network | pt_PT |
| dc.subject | K-Nearest Neighbors | pt_PT |
| dc.subject | Decision Tree | pt_PT |
| dc.subject | SDG 9 - Industry, innovation and infrastructure | pt_PT |
| dc.title | Forecasting models for real estate market analysis The case study of Portugal | pt_PT |
| dc.type | master thesis | |
| dspace.entity.type | Publication | |
| rcaap.rights | openAccess | pt_PT |
| rcaap.type | masterThesis | pt_PT |
| thesis.degree.name | Mestrado em Gestão de Informação, especialização em Gestão do Conhecimento e Inteligência de Negócio (Business Intelligence) | pt_PT |