This website uses cookies so that we can provide you with the best user experience possible. Cookie information is stored in your browser and performs functions such as recognising you when you return to our website and helping our team to understand which sections of the website you find most interesting and useful.
Detalhes da Produção
Tipo | Artigo Publicado |
Grupo | Produção Bibliográfica |
Descrição | BALANIUK, R. ; do Prado, Hércules Antonio ; Guadagnin, R. ; FERNEDA, Edilson ; COBBE, P.. Predicting evasion candidates in higher education institutions. Lecture Notes in Computer Science, v. 6918, p. 143-151, 2011. |
Autor | Hercules Antonio do Prado |
Ano | 2011 |
Informações Complementares
Ano do artigo | 2011 |
Descricão e Informacões Adicionais | Abstract: Since the nineties, Data Mining (DM) has shown to be a privileged partner in business by providing the organizations a rich set of tools to extract novel and useful knowledge from databases. In this paper, a DM application in the highly competitive market of educational services is presented. The course abandonment problem by students represents a serious risk for the education service providers. Identifying students who intend to transfer to a competing school, or to drop out altogether, before they initiate the transfer process or simply stop attending classes has been a very difficult proposition for colleges or universities. Prior research indicates that student retention plays an important role in achieving advantage over competitors, since it translates into a solid financial base onto which to build the educational services business. Additionally, an increased graduation rate contributes to fulfilling the education service provider s social charter, which is to better prepare a new generation of citizens. This paper presents a successful data mining application for evasionrisk prediction in a higher education institution in the Federal District of Brazil. A model was built by combining a set of classifiers into a committee machine to predict the likelihood that a student who completed his/her second term will remain in the institution until graduation. The model has shown to be predictive for evasion in a high accuracy level and has been useful for managing the students portfolio. |
Divulgacão Científica | NAO |
Idioma | Inglês |
ISSN | 03029743 |
Meio de Divulgação | NAO_INFORMADO |
Natureza | COMPLETO |
Página Final | 151 |
Página Inicial | 143 |
Relevância | NAO |
Título do Artigo | Predicting evasion candidates in higher education institutions |
Título do Períodico ou Revista | Lecture Notes in Computer Science |
Volume | 6918 |