A carregar...
Publicação
EURIBOR Fluctuations and Property Values: A Machine Learning Comparison of Portugal and Spain
| Nome: | Descrição: | Tamanho: | Formato: | |
|---|---|---|---|---|
| 1.29 MB | Adobe PDF |
Autores
Orientador(es)
Resumo(s)
This study explores the predictive relationship between macroeconomic, demographic, and
financial variables and the 6-month EURIBOR rate, examining how its fluctuations shape
housing market dynamics in Portugal and Spain. Employing the XGBoost machine learning
algorithm and lagged feature engineering to reflect real-world forecasting constraints, the
analysis achieved strong predictive performance, with out-of-sample R² values of 0.8161 for
Portugal and 0.7803 for Spain and corresponding Mean Absolute Errors (MAE) of 0.1703 and
0.1788, respectively. Short-term EURIBOR tenors (1-week, 1-month, 3-month) and the 12-
month rate were the most influential predictors across both countries, showing their role in
capturing market expectations about future monetary policy. Despite the similarities,
important national differences were identified. In Spain, macroeconomic indicators such as
GDP and unemployment exhibited a higher relative importance, suggesting that Spanish
interest rate dynamics are more sensitive to broad economic conditions. In contrast,
Portugal’s model revealed a stronger influence of demographic factors, indicating that
structural population trends significantly shaped its interest rate environment. These findings
carry theoretical and practical implications. The results affirm the differentiated transmission
of common monetary policy across national markets within the Eurozone, and the study
points out the need for localized forecasting models, particularly given the variations in
mortgage structures. Portugal’s high prevalence of variable-rate mortgages contrasts Spain’s
growing share of fixed-rate lending. The study demonstrates the power of combining machine
learning techniques with economic theory to forecast key financial indicators, providing
valuable insights for policymakers, investors, and financial institutions navigating an
increasingly complex and heterogeneous European interest rate situation.
Descrição
Dissertation presented as the partial requirement for obtaining a Master's degree in Data Driven Marketing, specialization in Data Science for Marketing
Palavras-chave
EURIBOR Housing Market Cross Country Analysis XGBoost Optuna SHAP Interpretability SDG 8 - Decent work and economic growth SDG 9 - Industry, innovation and infrastructure SDG 10 - Reduced inequalities SDG 11 - Sustainable cities and communities