A carregar...
Publicação
Multivariate Analysis of Sustainable Data in Energy Utility - Clustering Analysis Application in Contributing Locations
| Nome: | Descrição: | Tamanho: | Formato: | |
|---|---|---|---|---|
| 1.55 MB | Adobe PDF |
Autores
Orientador(es)
Resumo(s)
With the increase of amount of data generated, finding a way to get knowledge and insights from them is fundamental in decision-making for any kind company in any field. For a company as EDP, an electric utility, and its responsibilities and commitments entailed its crucial to meet the expectations of its customers and investors, otherwise it is in danger of losing its reputation and money to its competitors. With this in mind and being that I was in the team responsible for collecting the sustainable data from the locations belonging to EDP Group, we decided to move forward to an analysis of the reporting process and by complementing it by analysing a clustering solution to characterize the diverse locations. This project followed CRISP-DM methodology from the beginning until the end where the clustering solution was found by applying hierarchical clustering on top of K-means. All the data understanding, transformation, modeling and model evaluation was performed using Jupyter Notebook, being the final solution built in Power BI platform.
Descrição
Internship Report presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics, specialization in Business Analytics
Palavras-chave
Sustainability Reporting CRISP-DM Methodology Data Mining Unsupervised Learning Clustering