Machine learning classifiers do not improve the prediction of academic risk: Evidence from Australia

Cornell-Farrow, Sarah; Garrard, Robert

doi:10.1080/23737484.2020.1752849

Cited by 9 publications

(7 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Interestingly, there are times when such ML methods do not outperform conventional linear regression (e.g. Cornell-Farrow, & Garrard, 2020;Kotsiantis et al, 2004). Several reasons have been put forth; some authors argue that when ML methods are used with sample sizes that are too small, any non-linearities present may go undetected (Huang & Fang, 2013;Kotsiantis et al, 2004).…”

Section: Use Of ML Methods For Predicting Academic Performancementioning

confidence: 99%

Predicting Students’ Academic Performance: A Comparison between Traditional MLR and Machine Learning Methods with PISA 2015

Puah¹

2021

Preprint

View full text Add to dashboard Cite

Predicting students’ academic performance has long been an important area of research in education. Most existing literature have made use of traditional statistical methods that run into the problems of overfitted models, inability to effectively handle large numbers of participants and predictors, and inability to pick out non-linearities that may be present. Regression-based ML methods that can produce highly interpretable yet accurate models for new predictions, are able to provide some solutions to the aforementioned problems. The present study is the first study that develops and compares between traditional MLR methods and regression-based ML methods (i.e. ridge regression, LASSO regression, elastic net, and regression trees) to predict students’ science performance in the PISA 2015. A total of 198,712 students from 60 countries, and 66 student- and school-related predictors were used to develop the predictive models. Predictive accuracy of the various models built were not that different, however, there were significant differences in the predictors identified as most important by the different methods. Although regression-based ML techniques did not outperform traditional MLR, significant advantages for using ML methods were noted and discussed. Moving forward, we strongly believe that there is merit for using such regression-based ML methods in educational research. Educational research can benefit from adopting ML practices and methods to produce models that can not only be used for explaining factors that influence academic performance prediction, but also for making more accurate predictions on unseen data.

show abstract

Section: Use Of ML Methods For Predicting Academic Performancementioning

confidence: 99%

Predicting Students’ Academic Performance: A Comparison between Traditional MLR and Machine Learning Methods with PISA 2015

Puah¹

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Similar to the previous reference in ref [15], the authors employed linear regression (accuracy = 64.25), decision tree (accuracy = 59.8), and naive Bayes (accuracy = 71) algorithms in data analysis with 303 input features including student demographics, the salaries of educators, and assessment data. Moreover, in ref [12], logistic regression (accuracy = 0.839), elastic net (accuracy = 0.839), decision tree (accuracy = 0.767), random forest (accuracy = 0.828) and neural network (accuracy = 0.833) algorithms were utilized to evaluate student performance in English lessons. Their database was NA-PLAN which is a set of standardized literacy and numeracy tests sat by all students in Australia and the tests cover five learning areas known as "test domains" (reading, writing, spelling, grammar and punctuation, and numeracy), alongside student background information which is collected by schools from students' parents via enrolment forms.…”

Section: Evaluation Of Student Performancementioning

confidence: 99%

“…In this study, student performance was evaluated by supervised ML models. Studies that had similar data have used random forest [42][43][44], gradient boosting [41], support vector machines (SVM) [45][46][47], elastic net [12], naive Bayes [15,34,48], logistic regression [12,41,49], decision tree [42,50,51], and ANN [52][53][54] algorithms. Therefore, the preprocessed data executed on previously mentioned models and best performance with the default parameters were obtained by RF, SVM and LR models; Thus, these models were selected for more tuning and analysis.…”

Section: Model Selectionmentioning

confidence: 99%

“…Machine learning and data mining are powerful tools for instructors and institutions to explore the educational database; this has increased with the assistance of ML, and enabled decision-makers to extract information from data for decisions and policies. The application that ML uses in the educational database is called Educational Data Mining (EDM) [11,12]. The educational database is available at different levels of detail for different tasks and often expands in several software systems over some time [13].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Practical Model for the Evaluation of High School Student Performance Based on Machine Learning

et al. 2021

View full text Add to dashboard Cite

The objective of this research is to develop an machine learning (ML) -based system that evaluates the performance of high school students during the semester and identify the most significant factors affecting student performance. It also specifies how the performance of models is affected when models run on data that only include the most important features. Classifiers employed for the system include random forest (RF), support vector machines (SVM), logistic regression (LR) and artificial neural network (ANN) techniques. Moreover, the Boruta algorithm was used to calculate the importance of features. The dataset includes behavioral information, individual information and the scores of students that were collected from teachers and a one-by-one survey through an online questionnaire. As a result, the effective features of the database were identified, and the least important features were eliminated from the dataset. The ANN accuracy, which was the best accuracy in the original dataset, was reduced in the decreased dataset. On the contrary, SVM performance was improved, which had the highest accuracy among other models, with 0.78. Moreover, the LR and RF models could provide the same performance in the decreased dataset. The results showed that ML models are influential for evaluating students, and stakeholders can use the identified effective factors to improve education.

show abstract

“…Es preciso indicar que estudios previos que tratan de identificar las variables que explican el rendimiento académico (López-García & Gutiérrez-Niño, 2018), señalan el nivel socioeconómico (Masci et al, 2018;Maulida & Kariyam, 2017;Rodríguez-Hernández et al, 2021;Salal & Abdullaev, 2020), el género (Abdul-Aziz et al, 2015;Chacón-Vargas & Roldán-Villalobos, 2021;Guo et al, 2015), la ubicación geográfica de las instituciones (Ariza et al, 2021;Froiland & Oros, 2014;Lau et al, 2019), los antecedentes académicos de los estudiantes (Abdul-Aziz et al, 2015;Chacón-Vargas & Roldán-Villalobos, 2021;Febro, 2019;Chaparro Rodríguez, Jaimes Márquez & Prada Núñez, 2018), los recursos materiales que disponen los estudiantes y las instituciones (Ariza et al, 2021;Castrillón et al, 2020;Masci et al, 2018;Claro-Vásquez, 2017), la formación previa de los padres (Chacón-Vargas & Roldán-Villalobos, 2021;Cornell-Farrow & Garrard, 2020;Galster et al, 2016;Kumari et al, 2018), la experiencia docente (Ariza et al, 2021;Castrillón et al, 2020;Cavadia, Payares, Herrera, JAramillo & Meza, 2019;Khan & Ghosh, 2018;Lisboa-Bartholo & Da-Costa, 2016), entre otras, como las variables predominantes, sin embargo, no se identifica evidencia contundente y empírica asociada a la adicción a las Redes Sociales y la Internet (RSI), que influyan en la obtención del logro de aprendizaje (Espinel-Rubio, Hernández-Suárez & Rojas-Suárez, 2020;Gentile et al, 2014). Para Mira y Ruiz Callado (2017), el consumo de drogas y el regreso a casa, se constituyeron en variables productoras de rendimiento acad...…”

Section: Introductionunclassified

Factores de riesgo en jóvenes escolarizados asociados al uso de las redes sociales y la internet

Suárez

Cárdenas

2022

rev.perspect

View full text Add to dashboard Cite

El objetivo de este artículo es develar las variables subyacentes al uso de las redes sociales e internet, en jóvenes estudiantes de educación básica, de un colegio citadino en Colombia. Las categorías desde las que se estudia la adicción-adolescentes son: síntomas-adicción, uso-social, rasgos-frikis y nomofobia. El enfoque metodológico es cuantitativo, el instrumento utilizado es Escala de Riesgo de Adicción-adolescente a las Redes Sociales e Internet, adicionalmente se utilizaron los índices de fiabilidad y el análisis de componentes principales, para determinar las variables subyacentes. En la investigación participaron 179 jóvenes cuyas edades están entre 12 y 16 años. El alfa de Cronbach global es de 0,867. Las variables subyacentes identificadas son: Socialización, Amistad con Tecnologías de la Información y la Comunicación, Comunicación Grupal Dependiente-multipropósito, Síntomas de Adicción Relevantes, Tiempo de Ocio en Redes Sociales y la Internet y uso de las Redes Sociales como Fuente de Información Sobre Sexualidad. El estudio no es concluyente en determinar la existencia de la adicción a las redes sociales y la internet, sin embargo, se develan algunas variables a considerar para prever factores de riesgo a considerar en el ámbito escolar

show abstract

Machine learning classifiers do not improve the prediction of academic risk: Evidence from Australia

Cited by 9 publications

References 24 publications

Predicting Students’ Academic Performance: A Comparison between Traditional MLR and Machine Learning Methods with PISA 2015

Predicting Students’ Academic Performance: A Comparison between Traditional MLR and Machine Learning Methods with PISA 2015

A Practical Model for the Evaluation of High School Student Performance Based on Machine Learning

Factores de riesgo en jóvenes escolarizados asociados al uso de las redes sociales y la internet

Contact Info

Product

Resources

About