Enhanced Model for Predicting Student Dropouts in Developing Countries Using Automated Machine Learning Approach: A Case of Tanzanian’s Secondary Schools

Mnyawami, Yuda N.; Maziku, Hellen; Mushi, Joseph Cosmas

doi:10.1080/08839514.2022.2071406

Cited by 15 publications

(4 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The obtained dataset was used to train and evaluate supervised machine learning algorithms like Logistic Regression, Decision Tree, Random Forest, Naive Bayes, K-nearest Neighbors, Linear Discriminant Analysis, and Stochastic Gradient Descent using classic and improved methods. The study reuses student dropout features presented in previous work by (Mnyawami et al, 2022). The experiments showed the improvement of the prediction results using the Bayesian Optimization approach.…”

Section: Feature Engineeringmentioning

confidence: 95%

“…These approaches suffer from the feature, algorithm selection for the corresponding hyperparameter values that lessen prediction accuracy of the model (Tuggener et al, 2019). The automated machine learning techniques has been the promising method to accurately identify potential features that lead student to dropout (Mnyawami et al, 2022). The improvement of the prediction model can be achieved by the automation of machine learning algorithms which consists of grid search, randomized search and Bayesian hyperparameter optimization techniques (Yang & Shami, 2020).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Implementation of Bayesian Hyperparameter Optimization for Predicting Student Dropout in Sub-Saharan Africa Secondary Schools

Mnyawami

Maziku

Mushi

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Many secondary schools in Sub-Saharan countries face the problem of students dropping out of school due to various reasons which are difficult to diagnose directly. Various initiatives such as the big results now initiatives, free education for all, no child left behind, and secondary education development programme as well as machine learning prediction models used to reduce the severity of the problem in Sub-Saharan countries. The ongoing dropout problem, particularly in secondary schools, is ascribed to improper root cause identification and the absence of formal procedures that may be used to estimate the severity of the issue. Bayesian Optimization technique has been used to project the student dropout by optimizing the prediction results. The forecast accuracy of machine learning algorithms is hampered by default optimization techniques, making it difficult to pinpoint the real causes of student dropouts. The performance of the optimized model was evaluated by the average accuracy, precision, recall, f1, Roc curve, and AUC. Prediction accuracy results indicate that NB = 95%, LDA = 94%, SGD = 96%, DT = 97%, RF = 97%, LR = 96%, KNN = 97%, and AdaBoost = 97%. Features including student marks, age, school distance, parental education, number of children, and parental occupation significantly contribute to student dropouts. Results indicate the prediction accuracy of the proposed model outperforms the default optimization method of the machine learning algorithms. A well-optimized strategy draws a lot of attention to the findings related to student dropout rates in Sub-Saharan countries.

show abstract

Section: Feature Engineeringmentioning

confidence: 95%

Section: Introductionmentioning

confidence: 99%

Implementation of Bayesian Hyperparameter Optimization for Predicting Student Dropout in Sub-Saharan Africa Secondary Schools

Mnyawami

Maziku

Mushi

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Chung and Lee (2019) employed random forests to predict dropout among Korean high school students, though predictors of non-dropouts were stronger. These analyses highlight the importance of non-academic measures for understanding the impact of absenteeism and school dropout risk (see also Colak Oz et al, 2023;Mnyawami et al, 2022;Selim & Rezk, 2023).…”

Section: Algorithm-based Analysesmentioning

confidence: 99%

Translating sophisticated data analytic strategies regarding school attendance and absenteeism into targeted educational policy

Kearney

Childs

2023

Improving Schools

View full text Add to dashboard Cite

School attendance and absenteeism are critical targets of educational policies and practices that often depend heavily on aggregated attendance/absenteeism data. School attendance/absenteeism data in aggregated form, in addition to having suspect quality and utility, minimizes individual student variation, distorts detailed and multilevel modeling, and obscures underlying causes and disparities of absenteeism. Recent advances in data analytics/mining and modeling may assist researchers and other stakeholders by evaluating large-scale data sets in more targeted ways to identify key root causes and patterns of school absenteeism in a particular community, school, or group of students. This would allow for more accurate educational policies tailored to unique local conditions and student/family circumstances. This article provides a summary of recent algorithm- and model-based efforts in this regard. Algorithm-based efforts include classification and regression tree analysis, ensemble analysis, support vector machines, receiver operating characteristic analysis, and random forests. Model-based efforts include multilevel modeling, structural equation modeling, latent class analysis, and meta-analytic modeling. We then illustrate how these efforts can enhance a full and nuanced understanding of the root, interconnected causes of absenteeism, improve early warning systems, and assist multi-tiered systems of support interventions for absenteeism.

show abstract

“…As variáveis relevantes para a análise incluíram notas dos alunos (57%), idade do aluno (18%), RBIE v.32 -2024 distância (7%) e número de crianças (5%). (Mnyawami et al, 2022).…”

Section: Estudos Que Utilizaram Métodos Clássicosunclassified

Investigação da Evasão Estudantil por meio da Mineração de Dados e Aprendizagem de Máquina: Um Mapeamento Sistemático

Jesus,

Gusmão

2024

RBIE

View full text Add to dashboard Cite

A evasão dos alunos nas escolas e universidades é um problema recorrente na educação, tanto é danoso para o aluno em termos de aprendizagem, como gera prejuízos financeiros para as instituições, sejam públicas ou privadas. Estudos que utilizam técnicas de mineração de dados (MD) e aprendizado de máquina (AM) para investigar problemas na educação estão em ascensão. A evasão estudantil é um desses problemas. Por meio dessas técnicas, é possível identificar padrões em indivíduos ou grupos que possam vir a abandonar os estudos. Este artigo tem como objetivo mapear sistematicamente artigos no estado da arte sobre a aplicação de DM e ML na classificação de dados em estudos sobre evasão escolar. A busca foi realizada em 5 bases de dados bibliográficas, ACM Digital Library, IEEE Xplore, Scopus, ScienceDirect e Web of Science, e retornou um total de 336 estudos primários. Após a aplicação dos critérios de exclusão e inclusão, restaram 71 estudos relevantes. Após a extração de dados desses estudos, identificou-se que, as experiências com estudantes do ensino superior e na modalidade presencial são as mais recorrentes nesses artigos, o ano que mais se destacou em termos de publicação foi 2020, e os algoritmos mais frequentemente utilizados para construção dos modelos de classificação são algoritmos baseados em árvores de decisão.

show abstract

Enhanced Model for Predicting Student Dropouts in Developing Countries Using Automated Machine Learning Approach: A Case of Tanzanian’s Secondary Schools

Cited by 15 publications

References 41 publications

Implementation of Bayesian Hyperparameter Optimization for Predicting Student Dropout in Sub-Saharan Africa Secondary Schools

Implementation of Bayesian Hyperparameter Optimization for Predicting Student Dropout in Sub-Saharan Africa Secondary Schools

Translating sophisticated data analytic strategies regarding school attendance and absenteeism into targeted educational policy

Investigação da Evasão Estudantil por meio da Mineração de Dados e Aprendizagem de Máquina: Um Mapeamento Sistemático

Contact Info

Product

Resources

About