Analysis of Airbnb in Portugal in the Lisbon and Porto Regions: Data Integration and Analysis through Fabric

Abstract

Tourism is one of Portugal's main economic drivers. The country attracts tourists because of its climate, gastronomy and safety. There are more and more requirements and peculiarities that accommodation must meet to provide a pleasant experience. Airbnb is a platform that connects travellers with different types of accommodations. Through this application, the user can access different accommodations around the world and make a reservation. This project aims to process, work and analyse the data provided by the website Inside Airbnb - Get the Data for Portugal, focusing on the Lisbon and Porto areas. Through this information, the expectation is to build an analysis of the influence of this platform in Portugal, discovering patterns, trends and relationships between prices, reviews, number of customers, type of accommodation, region, among other relevant data. In the first phase, an analysis of the collected data will be carried out in order to define the appropriate structure for processing and analysing the data. Then, using Microsoft Fabric, a pipeline will be created to load the data into a data lake, transform the collected data, establish links between the information, and create new measures to aid in this analysis. This will set the stage for the creation of a report in Power BI from which the desired insights, such as prices, location, accommodation characteristics and the comparison of the Lisbon and Porto regions, could be made.