01.1 - Graduação (Sede)
URI permanente desta comunidadehttps://arandu.ufrpe.br/handle/123456789/2
Navegar
3 resultados
Resultados da Pesquisa
Item Sistema de suporte à criação de modelos de classificação para a previsão de evasão no ensino superior(2024-03-08) Costa, Tarcísio Barbosa da; Alencar, Andrêza Leite de; Albuquerque Júnior, Gabriel Alves de; http://lattes.cnpq.br/1399502815770584; http://lattes.cnpq.br/6060587704569605; http://lattes.cnpq.br/6560255346406064Student dropout is one of the greatest challenges faced by university degree institutions. In order to mitigate it, those institutions develop moitoring and analysis tools regarding this phenomenon. One of many existing methodologies to do so is the recognition of student characteristics that leads to dropout, and ond of many existing tools is SABIA: a virtual dashboard responsible for supporting evidence-based management allied to concepts like Learning/Academic Analytics and Business Intelligence. This work expands SABIA through a new page able to create user-customizable supervisioned learning models, offering feature analysis from students and predicting their final status based on those features. Information obtained through those models enables the recognition of risk features on student profiles and assists managers on providin guidelines for applying countermeasures against dropout.Item Análise da evasão no ensino superior: predição e prevenção por meio da mineração de dados educacionais(2024-03-05) Ferreira, Rodolfo André Barbosa; Mello, Rafael Ferreira Leite de; http://lattes.cnpq.br/6190254569597745; http://lattes.cnpq.br/2982020271806247Considering that dropout occurs due to abandonment, transfer, or withdrawal from the course; when the student disengages from the institution they are enrolled in or when the student definitively abandons or does not complete higher education, this article seeks to identify methods and automated techniques to assist managers in preventing dropout cases through predictions. To conduct the study, Educational Data Mining (EDM) was used, which applies data mining techniques such as database, statistics, and machine learning in education. Data from 5144 students with characteristics related to course, semester, and demographics were used from the database provided by the Academic Information and Management System (SIGA) of the Federal Rural University of Pernambuco (UFRPE) for the courses of Animal Science, Fisheries Engineering, and Agronomy. The data, except for those containing personal, restricted, and sensitive information, were separated into Academic Characteristics per Semester, General Academic Characteristics, Course-related, Demographic, and Target Characteristics. The study employs the LSTM machine learning algorithm and the SGD and Adam optimizers, exploring different values for the parameters of learning rate, momentum, batch size, and number of epochs.Item Uso de análise de sobrevivência como ferramenta na obtenção de indicadores de permanência no ensino superior(2024-03-06) Silva, Lhaíslla Eduarda Cavalcanti Rodrigues da; Albuquerque Júnior, Gabriel Alves de; http://lattes.cnpq.br/1399502815770584; http://lattes.cnpq.br/7477398253297436This paper proposes an integrated approach of statistical techniques, business intelligence and data science concepts to create a survival analysis model aimed at understanding student retention in higher education. Using computer science courses as a case study, different groups are compared in order to calculate the probability of students staying until the end of the course. The work makes use of the SABIA platform to support data-driven management, highlighting the importance of technological tools in academic analysis. The results show patterns between courses in the same area when considering dropout as an event of interest, with steeper drops in the initial periods, especially at critical moments, such as the second semester, which show lower probabilities of permanence compared to the first semester, as well as the Other entry modality, which in the final periods reflects the occurrence of dropout, highlighting the importance of personalised interventions to prevent dropout and waste of resources, contributing to more efficient and effective management of higher education institutions.