Predicting the Probability of Student Dropout through EMIR Using Data from Current and Graduate Students

Murakami, Katsuhiko; Takamatsu, Kunihiko; Kozaki, Yasuhiro; Kishida, Aoi; Bannaka, Kenya; Noda, Ikuhiro; Jyunichiro, Asahi; Takao, K.; Mitsunari, Kenichiro; Nakamura, Tadashi; Nakata, Yasuo

doi:10.1109/iiai-aai.2018.00103

Cited by 9 publications

(5 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Como dito na Etapa 1, obteve-se 50 trabalhos selecionados resultantes das buscas realizadas (Tabelas 3 e 4). E40 [Limsathitwong et al 2018] E27 [Jamesmanoharan et al 2014] E41 [Murakami et al 2018] E28 [Yukselturk et al 2014] E42 [Perez et al 2018] E29 [Pradeep et al 2015] E43 [Solis et al 2018] E30 [Marbouti et al 2016] E44 [Alban and Mauricio 2019] E31 [Meedech et al 2016] E45 [Li et al 2019] E32 [Ahuja and Kankane 2017] E46 [Beltran et al 2019] E33 [Pereira and Zambrano 2017] E47 [Lottering et al 2020] E34 [Rocha et al 2017] E48 [Utari et al 2020] E35 [Rodrıguez-Maya et al 2017] E49 [Viloria et al 2020] E36 [Rovira et al 2017] E50 [Yaacob et al 2020 Como mostram as Tabelas 3 e 4, dentre os trabalhos selecionados, 22 são nacionais e 28 internacionais. Pode-se dizer que há um equilíbrio entre as quantidades de trabalhos encontrados para cada cenário.…”

Section: Resultados E Discussõesunclassified

Uma análise de trabalhos de mineração de dados educacionais no contexto da evasão escolar

Santos

Saraiva

Oliveira

2021

Anais Do XXXII Simpósio Brasileiro De Informática Na Educação (SBIE 2021)

View full text Add to dashboard Cite

Este artigo apresenta uma análise de trabalhos de mineração de dados educacionais (Educational Data Mining - EDM) nacionais e internacionais que tratam da temática da evasão escolar. As buscas por trabalhos foram realizadas com o propósito de responder a sete questões de pesquisa sobre ferramentas/bibliotecas, algoritmos e bases de dados considerados nos trabalhos. Dada a grande quantidade de informações analisadas, foi utilizada a ferramenta Tableau para uma melhor compreensão e comparação dos fatores estudados. Os resultados servem como subsídio para otimizar a tomada de decisão de analistas de dados no planejamento e desenvolvimento de projetos de EDM.

show abstract

Section: Resultados E Discussõesunclassified

Uma análise de trabalhos de mineração de dados educacionais no contexto da evasão escolar

Santos

Saraiva

Oliveira

2021

Anais Do XXXII Simpósio Brasileiro De Informática Na Educação (SBIE 2021)

View full text Add to dashboard Cite

show abstract

“…Costa et al (2017), using a database of 262 students and a support vector machine, obtained up to 92% accuracy in the early prediction of students' academic failure in introductory programming courses. For their part, Murakami et al (2019) found up to 95% accuracy using logistic regression. This test is more accurate when using data from both current and graduate students than when only examining data from graduate students.…”

Section: Introductionmentioning

confidence: 99%

Prediction of student attrition risk using machine learning

Barramuño

Meza-Narváez

Gálvez‐García

2021

JARHE

View full text Add to dashboard Cite

PurposeThe prediction of student attrition is critical to facilitate retention mechanisms. This study aims to focus on implementing a method to predict student attrition in the upper years of a physiotherapy program.Design/methodology/approachMachine learning is a computer tool that can recognize patterns and generate predictive models. Using a quantitative research methodology, a database of 336 university students in their upper-year courses was accessed. The participant's data were collected from the Financial Academic Management and Administration System and a platform of Universidad Autónoma de Chile. Five quantitative and 11 qualitative variables were chosen, associated with university student attrition. With this database, 23 classifiers were tested based on supervised machine learning.FindingsAbout 23.58% of males and 17.39% of females were among the attrition student group. The mean accuracy of the classifiers increased based on the number of variables used for the training. The best accuracy level was obtained using the “Subspace KNN” algorithm (86.3%). The classifier “RUSboosted trees” yielded the lowest number of false negatives and the higher sensitivity of the algorithms used (78%) as well as a specificity of 86%.Practical implicationsThis predictive method identifies attrition students in the university program and could be used to improve student retention in higher grades.Originality/valueThe study has developed a novel predictive model of student attrition from upper-year courses, useful for unbalanced databases with a lower number of attrition students.

show abstract

“…The analysis of IR is categorized into three levels: the macro level as that between systems, the meso level as the organization level, and the micro level as the individual learner level. An example of meso-level study is the problem of dropout in higher education, which has progressed in the last few years [10] [11].…”

Section: Introductionmentioning

confidence: 99%

Introducing New Mass Screening in Institutional Research Based on Eduinformatics

Takamatsu

Itō

Kirimura

et al. 2022

IIAI Letters on Institutional Research

View full text Add to dashboard Cite

In recent years, student information has accumulated due to the increasing number of remote lectures during the COVID-19 pandemic and the digital transformation (DX) of education. Student information data were analyzed by faculty members. We propose a system called "mass screening" in this study, which follows a 2-steps method. First, we analyzed all the students at the university scale and department. Then, we returned the analysis reports to faculty members at Kobe Tokiwa University to prepare true tailor-made education. The university raised SSP, and the student support policy was able to raise early alerts for students.

show abstract

Predicting the Probability of Student Dropout through EMIR Using Data from Current and Graduate Students

Cited by 9 publications

References 7 publications

Uma análise de trabalhos de mineração de dados educacionais no contexto da evasão escolar

Uma análise de trabalhos de mineração de dados educacionais no contexto da evasão escolar

Prediction of student attrition risk using machine learning

Introducing New Mass Screening in Institutional Research Based on Eduinformatics

Contact Info

Product

Resources

About