| Nome: | Descrição: | Tamanho: | Formato: | |
|---|---|---|---|---|
| 1.89 MB | Adobe PDF |
Autores
Resumo(s)
This study addresses a significant gap in microeconomic tourism analysis for small regions by
developing a scalable, data-driven framework for Oeste CIM, Portugal, a region heavily reliant
on tourism and subject to seasonal economic fluctuations. Utilizing transactional records from
2021 to 2024, we implemented a Lakehouse architecture with Kimball dimensional modelling
to facilitate parish-level spending analysis. Automated ETL pipelines process payment data,
and CatBoost forecasting models predict tourism trends with a mean absolute percentage
error (MAPE) of less than 15%, surpassing traditional methods. The integrated Power BI
dashboard reveals critical microeconomic insights: weekends account for 70% of spending,
and sectors such as "Petrol Stations" and "Supermarkets" exhibit high economic resilience.
The findings validate the effectiveness of machine learning for forecasting in small regions
despite data limitations and provide stakeholders with actionable tools for resource
optimization. This framework transforms transactional data into strategic insights, enabling
municipalities and businesses to mitigate seasonal risks, enhance infrastructure planning, and
advance the Sustainable Development Goals (SDG 8–9). This solution offers a replicable
blueprint for data-driven urban planning in tourism economies globally.
Descrição
Dissertation presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics, specialization in Business Analytics
Palavras-chave
smart tourism smart region forecasting microeconomic indicators business intelligence SDG 8 - Decent work and economic growth SDG 9 - Industry, innovation and infrastructure SDG 11 - Sustainable cities and communities
