Accuracy Comparison of Machine Learning Algorithms for Predictive Analytics in Higher Education

Brohi, Sarfraz Nawaz; Pillai, Thulasyammal Ramiah; Kaur, Sarvjeet; Kaur, Harsimren; Sukumaran, S.; Asirvatham, David

doi:10.1007/978-3-030-23943-5_19

Cited by 17 publications

(9 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In relation to the sociodemographic factor, Yamao [67] seeks to predict the performance of students at the end of their first year of university and, through statistical techniques, manages to determine that the most influential variables in performance are gender, age, type of income and distance from their home to the study center. On the other hand, Brohi [74] shows that the most influential variables of the sociodemographic factor are those related to the relative responsible for the student and the nationality. Jayaprakash [54] classifies the variables according to their importance, and finds that the most relevant variables related to this factor are parental status, gender, family size and parental education.…”

Section: As For the Factorsmentioning

confidence: 99%

“…Regarding the psychosocial factor, Rahman [35] finds that these variables improve the performance of predictive models, especially the variable related to attendance (which is stated by Kostokopoulos [57] in his study, in which there is a progressive addition of variables to the training data to determine the level of improvement in the accuracy of their models), and indicates that the most relevant variables are attendance at face-to-face activities and delivery of written tasks. Brohi [74] and Jawthari [75] also show that the most influential variable in academic performance within the psychosocial factor is the one related to attendance.…”

Section: As For the Factorsmentioning

confidence: 99%

See 1 more Smart Citation

revisión sobre la predicción del rendimiento académico mediante métodos de ensamble

Rodríguez¹,

Silva²,

Bravo³

2022

ing. Solidar

View full text Add to dashboard Cite

Introducción: El presente artículo es producto de la investigación “Métodos de ensamble para estimar el ren-dimiento académico de estudiantes de educación superior”, desarrollado en la Universidad Distrital Francisco José de Caldas en el año 2021 y se centra en la revisión de trabajos de investigación desarrollados en los últimos cinco años relacionados a la predicción del rendimiento académico utilizando algoritmos de ensamble.Objetivo: La revisión de la literatura tiene como objetivo identificar los algoritmos más utilizados y las variables más relevantes en la predicción del rendimiento académico.Metodología: Se realizó una revisión sistemática de la literatura en distintas bases de datos académicas (Science Direct, Scopus, SAGE Journals, EBSCO, ResearchGate, Google Scholar), utilizando ecuaciones de bús-queda construidas con palabras claves.Resultados: Se encontraron 54 artículos relacionados que cumplen con los criterios de inclusión de la revisión. Además, se encontraron beneficios en la aplicación de métodos de ensamble en la predicción del rendimiento académico. Conclusión: Se encontró que las variables más influyentes en el rendimiento académico corresponden al factor académico, el algoritmo utilizado que presenta mejores resultados es Random Forest, además de que fue el más utilizado, y que el uso de estos algoritmos es una herramienta precisa para predecir el rendimiento acadé-mico en cualquier etapa de la vida universitaria, y a su vez brindar la información para generar estrategias que permitan mejorar los indicadores de deserción y retención académica.

show abstract

Section: As For the Factorsmentioning

confidence: 99%

Section: As For the Factorsmentioning

confidence: 99%

revisión sobre la predicción del rendimiento académico mediante métodos de ensamble

Rodríguez¹,

Silva²,

Bravo³

2022

ing. Solidar

View full text Add to dashboard Cite

show abstract

“…Another eight studies 23,[27][28][29][30][31][32][33] collected data from Kaggle, 34 and seven of them used dataset named xAPI-Edu-Data. 35 Two studies 36,37 used StudentPerformance 38 dataset from UCI Machine Learning Repository.…”

Section: Source Of Datamentioning

confidence: 99%

A survey on educational data mining methods used for predicting students' performance

Xiao

2021

Engineering Reports

View full text Add to dashboard Cite

Predicting students' performance is one of the most important issues in educational data mining (EDM), which has received more and more attention. By predicting students' performance, we can identify students' risk of academic failure and help instructors to take some actions such as guidance or interventions to help learners as early as possible, or carry out continual evaluation of learners as to optimize learning path or personalized learning resources recommendation. In this survey, we reviewed the 80 important studies on predicting students' performance using EDM methods in 2016-2021, synthesized the procedure of building prediction model of students' performance which contains four phases and 10 key steps, and compared and discussed the latest EDM methods used in all steps. We analyzed the challenges faced by previous studies in three aspects and put forward future suggestions on data collection, EDM methods used, and interpretation of prediction model. This survey provides a comprehensive understanding and practical guide for researchers in this field, and also provides direction for further research.

show abstract

“…Nowadays, several ML techniques are being developed for different applications. The main advancements are driven by the pursuit of faster learning processes (Castillo et al, 2006;Fu, 2017), more accurate predictions (Brohi et al, 2019;González-Sanchez et al, 2014), and the embedment of such algorithms into devices.…”

Section: Machine Learning: An Overview a Historical Perspective Of Ma...mentioning

confidence: 99%

Machine Learning Challenges and Opportunities in the African Agricultural Sector -- A General Perspective

2021

Preprint

View full text Add to dashboard Cite

Accuracy Comparison of Machine Learning Algorithms for Predictive Analytics in Higher Education

Cited by 17 publications

References 3 publications

revisión sobre la predicción del rendimiento académico mediante métodos de ensamble

revisión sobre la predicción del rendimiento académico mediante métodos de ensamble

A survey on educational data mining methods used for predicting students' performance

Machine Learning Challenges and Opportunities in the African Agricultural Sector -- A General Perspective

Contact Info

Product

Resources

About