Analysis of the Technology Extension Program from the Government of the state of Pernambuco Using Data Clustering Techniques

• Autor(a) principal: Freire, Victor Hugo Wanderley
• Data de Publicação: 2022
• Outros Autores: Bastos Filho, Carmelo José Albanez, Rabbani, Emilia Rahnemay Kohlman
• Tipo de documento: Artigo
• Idioma: por
• Título da fonte: Revista de Engenharia e Pesquisa Aplicada
• Texto Completo: http://revistas.poli.br/index.php/repa/article/view/2224

The growing demand for STEM professionals was accelerated by the COVID-19 pandemic. In Brazil, the low investment and incentive for this particular area generates a deficit of professionals, meaning that there are not as many professionals as the market demands. In the state of Pernambuco, this scenario is even worse, so the government of the state has launched a technological extension program (PET) aiming to decrease this deficit. This program has generated a great amount of data that needed to be studied, analyzed and processed in order to lead to a better understanding of the program and also make it better in the next rounds. Therefore, some clustering techniques were used, like Agglomerative Algorithm, k-Modes, SOM maps with the objective of analyzing and absorbing some insights from the data. The metrics utilized to evaluate those clusters were the silhouette coefficient, purity and elbow method. The clusters resulting from those techniques showed important features of the project, in addition it showed that the project is being well evaluated by the beneficiaries and, so, achieving its goal.