An Ensemble Predictive Model Based Prototype for Student Drop-out in Secondary Schools

Mduma, Neema; Kalegele, Khamisi; Machuve, Dina

doi:10.29333/jisem/5893

Cited by 12 publications

(7 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The model's purpose was to aid education stakeholders in detecting at-risk students and schools. This developed system can be used by authorities for planning and budgeting to satisfy school requirements [16]. Combining models always achieve best accuracy than individual models.…”

Section: Literature Reviewmentioning

confidence: 99%

Ensemble Machine Learning Model for University Students’ Risk Prediction and Assessment of Cognitive Learning Outcomes

Mary.T¹,

J²

2023

IJIET

View full text Add to dashboard Cite

One of the biggest challenges in higher educational institutions is to avoid students’ failures. Globally student dropout is a serious issue. Risk of dropouts can be identified at an earlier stage using machine learning classifiers, as they have gained more popularity in both academia and industry. The research team suggests that early prediction facilitates educators and higher education administrators to take necessary measures to prevent dropouts. Data for the research were collected from 530 Indian students when they were engaged in online learning during pandemic crisis. This research work involves two phases. In first phase, hybrid ensemble strategy is focused that integrates two powerful machine learning algorithms namely Random Forest (RF) and eXtreme Gradient Boosting (XGBoost) for early at-risk prediction. The result is a fast procedure for classification of at-risk students which is competitive in accuracy and highly robust. Prediction models are developed using ensemble learning, furthermore ensemble models are combined into a single meta-model, which provides best outcomes to enable higher education institutions for predictive analysis. Moreover, it correctly classified students’ at-risk regarding accuracy, precision, recall and F1-score with values of 93%, 91.52%, 96.42% and 93.91% respectively. In second phase, prediction model is deployed by creating a web application using. Net framework to sense students’ sentiments using Azure cognitive services text analytics (Application Programming Interface) API for detecting cognitive behavioral outcomes in online learning environment.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Ensemble Machine Learning Model for University Students’ Risk Prediction and Assessment of Cognitive Learning Outcomes

Mary.T¹,

J²

2023

IJIET

View full text Add to dashboard Cite

show abstract

“…The authors report an accuracy of 88.8% using the C4.5 algorithm. The work of Mduma et al (2019) focuses on the use of artificial intelligence in developing an ensemble predictive based prototype to help education stakeholders in the early detection of student dropout in secondary schools. Using a dataset from Tanzania from 2015 consisting of 61,340 instances their model combines logistic regression and multilayer perceptron models.…”

Section: Literature Reviewmentioning

confidence: 99%

Index, Volume 3, 2022

2022

J Mach Learn Model Comput

View full text Add to dashboard Cite

The Journal of Machine Learning for Modeling and Computing (JMLMC) focuses on the study of machine learning methods for modeling and scientific computing. The scope of the journal includes, but is not limited to, research of the following types: (1) the use of machine learning techniques to model real-world problems such as physical systems, social sciences, biology, etc.; (2) the development of novel numerical strategies, in conjunction of machine learning methods, to facilitate practical computation; and (3) the fundamental mathematical and numerical analysis for understanding machine learning methods.

show abstract

“…Studies in African countries also show that students' dropout was an issue. The Ghana Statistical Service (GSS) carried out a survey that showed that as high as 25% of youth who should be in Senior High School are not in school (Yusuf, 2019); the rate of student dropout in Tanzanian secondary schools is about36% (Mduma, 2019). The Kenyan government intended to make education affordable and accessible to all children in Kenya (Musangi et al, 2017) as well as address the low completion rates (Oprong, 2016) through free primary education (FPE) and free day secondary education (FDSE).…”

Section: Introductionmentioning

confidence: 99%

Social Media as a Determinant of Students’ Dropout Rates in Secondary Schools in Kenya

Muthami,

Mwania,

Cheloti

2023

BJMAS

View full text Add to dashboard Cite

Education is the natural right of every human being and is an integral part of every human life. The purpose of the study was to investigate the influence of social media on secondary school students’ dropout in public day secondary schools in Kenya. The article is an extract from a study done in public day secondary schools in Kitui central sub-county, Kitui County, Kenya. The study was guided by Bertalanffy’s Systems Theory. The study adopted descriptive survey research design. The study population was 25 schools and a sample size of 384 comprising of 22 principals, 22 form three class teachers and 340 form three students. Questionnaires for principals, class teachers and students were used to collect both quantitative and qualitative data. Data analysis was done using Statistical Package for Social Sciences (SPSS) version 26. The corelation analysis results on principals’ responses showed a strong correlation (r=0.675. p=0.006) between social media and students’ dropout rate. A strong correlation (r =0.612, p =0.022) between social media and students’ dropout rates was also shown when the class teachers’ responses were analysed. However, corelation analysis of the students’ responses showed a weak correlation (r=0.214, p=0.041). The researcher therefore concluded that students drop out of school is influenced by social media. The study thus recommended that the community, teachers, and parents should educate students on good use of social media so as not to misuse it.

show abstract

An Ensemble Predictive Model Based Prototype for Student Drop-out in Secondary Schools

Cited by 12 publications

References 19 publications

Ensemble Machine Learning Model for University Students’ Risk Prediction and Assessment of Cognitive Learning Outcomes

Ensemble Machine Learning Model for University Students’ Risk Prediction and Assessment of Cognitive Learning Outcomes

Index, Volume 3, 2022

Social Media as a Determinant of Students’ Dropout Rates in Secondary Schools in Kenya

Contact Info

Product

Resources

About