A carregar...
Publicação
Lisbon´s Real Estate Analysis based on Proximity Calculations
| Nome: | Descrição: | Tamanho: | Formato: | |
|---|---|---|---|---|
| 1.32 MB | Adobe PDF |
Resumo(s)
The real estate market is always changing and evolving and with sustainability becoming an increasingly important topic, the way the price of a property is determined, and the factors taken in consideration, should evolve as well. Inspired by the popular concept of Smart Cities, more specifically the 15-minute city approach, which is a concept highly focused on accessibility and walkability in cities, different variables were calculated to assess each property’s accessibility and diversity of amenities. Both these factors are different for each property, depending on their location. This work presents an analysis of the real estate market in Lisbon where, aside from the physical attributes of a habitation, the diversity and accessibility to difference services in each location will be evaluated and integrated in the machine learning process. The goal is to know the impact of each calculated measure when predicting the price per meter value of each house, in order to help understand why similar houses across Lisbon have such distinctive prices. Both the Euclidean Distance and the Network Distance were used in the calculations. The distance to Tejo River and the number of commercial establishments within a 15-minute walk radius were two of the most important features in the predictive models tested. Three different methods were tested and improved, electing the Random Forest Regressor as the best the one and the one to be used in the final model. The final model had half of the variance in the target explained by the all the calculated features, which makes this analysis a potential good tool to help fill the gap of a predictive model that only factors in the physical characteristics of a house.
Descrição
Project Work presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics, specialization in Business Analytics
Palavras-chave
Lisbon Smart City Real Estate Accessibility Mobility SDG 11 - Sustainable cities and communities