Banca de QUALIFICAÇÃO: EDUARDO CARDOSO MELO

Uma banca de QUALIFICAÇÃO de MESTRADO foi cadastrada pelo programa.
STUDENT : EDUARDO CARDOSO MELO
DATE: 26/10/2021
TIME: 14:00
LOCAL: https://meet.google.com/gfj-pjdm-kpd
TITLE:

Prediction of school dropout at the Federal Institute of Minas Gerais with the support of Machine Learning techniques

KEY WORDS:

School Dropout, Machine Learning, Data Mining, IFMG

PAGES: 85
BIG AREA: Ciências Exatas e da Terra
AREA: Ciência da Computação
SUBÁREA: Metodologia e Técnicas da Computação
SUMMARY:

School dropout is a phenomenon characterized by being influenced by several variables, which makes the study to identify which factors contribute to the dropout of a student from their academic institution complex. In the last decade there has been a considerable expansion in the offer of higher education courses in Federal Education Institutions, especially due to public policies that have fostered improvements in the physical infrastructure and personnel of educational units, allowing individuals with the most varied profiles to start their studies and do make the task of understanding school dropout more complex for managers. Parallel to this scenario, the Machine Learning area has also expanded its application possibilities in the last decade to the most diverse areas, including education, providing different ways to analyze and understand the data that are generated in the environment of each institution/organization. In this context, this Dissertation Project aims to use Machine Learning techniques to predict the risk of school dropout in undergraduate courses at the Federal Institute of Science, Education and Technology of Minas Gerais (IFMG), as well as to identify which are the most common attributes associated with this phenomenon in the institution. The structuring and organization of the activities foreseen in this work will be supported by the CRISP-DM methodology. Using data from all IFMG campuses, three models with different approaches will be built, tested and evaluated. The model with the best performance will then be used to predict the dropout rate of currently enrolled students with an analysis made from various perspectives, such as by campus, area of knowledge and course modality (Bachelor's Degree, Degree or Technologist). A case study was carried out with data from the IFMG - Campus Bambuí to analyze the feasibility of the proposed study, which showed that the dropout analysis conducted by managers of this institution can benefit from the contributions provided by the application of Machine Learning techniques.

BANKING MEMBERS:
Presidente - 1857559 - FERNANDA SUMIKA HOJO DE SOUZA
Interno - 1985872 - EDIMILSON BATISTA DOS SANTOS
Externo à Instituição - LUIZ HENRIQUE DE CAMPOS MERSCHMANN - UFLA