Predicting key educational outcomes in academic trajectories: a machine-learning approach

Musso, Mariel; Hernández, Carlos Felipe Rodríguez; Cascallar, Eduardo

doi:10.1007/s10734-020-00520-7

Cited by 73 publications

(39 citation statements)

References 70 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The researchers concluded that the model they proposed could be used to determine academically unsuccessful student. Musso et al, (2020) proposed a machine learning model based on learning strategies, perception of social support, motivation, socio-demographics, health condition, and academic performance characteristics. With this model, he predicted the academic performance and dropouts.…”

Section: Literaturementioning

confidence: 99%

“…In the literature, the prediction of academic performance was made with many and various variables, various digital traces left by students on the internet (browsing, lesson time, percentage of participation) (Fernandes et al, 2019;Rubin et al, 2010;Waheed et al, 2020;Xu et al, 2019) and students demographic characteristics (gender, age, economic status, number of courses attended, internet access, etc.) (Bernacki et al, 2020;Rizvi et al, 2019;García-González & Skrita, 2019;Rebai et al, 2020;Cruz-Jesus et al, 2020;Aydemir, 2017), learning skills, study approaches, study habits (Ahmad & Shahzadi, 2018), learning strategies, social support perception, motivation, socio-demography, health form, academic performance characteristics (Costa-Mendes et al, 2020;Gök, 2017;Kılınç, 2015;Musso et al, 2020), homework, projects, quizzes (Kardaş & Güvenir, 2020), etc. In almost all models developed in such studies, prediction accuracy is ranging from 70 to 95%.…”

Section: Literaturementioning

confidence: 99%

See 1 more Smart Citation

Educational data mining: prediction of students' academic performance using machine learning algorithms

Yağcı

2022

Smart Learn. Environ.

215

View full text Add to dashboard Cite

Educational data mining has become an effective tool for exploring the hidden relationships in educational data and predicting students' academic achievements. This study proposes a new model based on machine learning algorithms to predict the final exam grades of undergraduate students, taking their midterm exam grades as the source data. The performances of the random forests, nearest neighbour, support vector machines, logistic regression, Naïve Bayes, and k-nearest neighbour algorithms, which are among the machine learning algorithms, were calculated and compared to predict the final exam grades of the students. The dataset consisted of the academic achievement grades of 1854 students who took the Turkish Language-I course in a state University in Turkey during the fall semester of 2019–2020. The results show that the proposed model achieved a classification accuracy of 70–75%. The predictions were made using only three types of parameters; midterm exam grades, Department data and Faculty data. Such data-driven studies are very important in terms of establishing a learning analysis framework in higher education and contributing to the decision-making processes. Finally, this study presents a contribution to the early prediction of students at high risk of failure and determines the most effective machine learning methods.

show abstract

Section: Literaturementioning

confidence: 99%

Section: Literaturementioning

confidence: 99%

Educational data mining: prediction of students' academic performance using machine learning algorithms

Yağcı

2022

Smart Learn. Environ.

215

View full text Add to dashboard Cite

show abstract

“…Miguéis et al (2018) using a dataset of 2459 higher education students employed naïve Bayes, support vector machine, decision tree, random forest, bagged trees and adaptive boosting trees classifiers to address an academic achievement five classes' problem. Musso et al (2020) called on a 655 university students' dataset and an artificial neural network to deal with a problem of classification between low and high levels of three different measures of AA. Mengash (2020) made use of artificial neural network, decision tree, support vector machine and a naïve Bayes classifiers to anticipate five classes of higher education AA from a sample of 2039 students in order to evaluate the admission criteria of a Saudi University.…”

Section: Literature Reviewmentioning

confidence: 99%

A machine learning approximation of the 2015 Portuguese high school student grades: A hybrid approach

et al. 2020

View full text Add to dashboard Cite

This article uses an anonymous 2014-15 school year dataset from the Directorate-General for Statistics of Education and Science (DGEEC) of the Portuguese Ministry of Education as a means to carry out a predictive power comparison between the classic multilinear regression model and a chosen set of machine learning algorithms. A multilinear regression model is used in parallel with random forest, support vector machine, artificial neural network and extreme gradient boosting machine stacking ensemble implementations. Designing a hybrid analysis is intended where classical statistical analysis and artificial intelligence algorithms are blended to augment the ability to retain valuable conclusions and well-supported results. The machine learning algorithms attain a higher level of predictive ability. In addition, the stacking appropriateness increases as the base learner output correlation matrix determinant increases and the random forest feature importance empirical distributions are correlated with the structure of p-values and the statistical significance test ascertains of the multiple linear model. An information system that supports the nationwide education system should be designed and further structured to collect meaningful and precise data about the full range of academic achievement antecedents. The article concludes that no evidence is found in favour of smaller classes.

show abstract

“…For many students, this transition causes stress, anxiety, and insecurity, often leading to poor academic performance. It may also lead to students dropping out [2,3]: the highest dropout rate, in fact, occurs in the first year of university, attributed to student difficulties adapting to a new teaching/learning environment [4][5][6][7][8].…”

Section: Introductionmentioning

confidence: 99%

Executive function assessment: Adaptation of the Amsterdam executive function inventory using Spanish first-year university students from two knowledge areas

et al. 2022

View full text Add to dashboard Cite

Objective Many university students have difficulties in adapting to autonomous learning due to executive functioning deficits. In the Spanish university context, there is a lack of reliable validated instruments for the evaluation of executive functioning. In this sense, the aim of this research is to present the process of adaptation and validation of the Amsterdam Executive Function Inventory (AEFI) for the evaluation of executive functioning in the Spanish context. Methods This study integrates two sequential processes: questionnaire translation and back-translation, and evaluation of the psychometric properties (exploratory and confirmatory factor analysis were conducted), reliability, validity and multigroup analysis to identify factorial invariance. An online questionnaire was used for data collection and R package lavaan software was administered to a sample of 519 first-year university students (270 females and 249 males). Results The exploratory factor analysis evidenced an interna structure of three factors with adequate internal consistency (Cronbach’s alpha higher than 0.70), endorsed in the confirmatory factor analysis that indicated an adequate goodness-of-fit-indexes for the model. The composite reliability showed values between 0.74 and 0.82, and the convergent (average variance extracted values ranged from 0.50 to 0.61) and discriminant validity were adequate. A multigroup-analysis showed the invariance factorial through the difference in the RMSEA, CFI and TLI index, performed both in the model comparison according to gender and academic disciplines. Conclusion The AEFI adapted for Spanish has practical implications for the management of university students, as it can facilitate the improvement of university policies designed to foster the development of executive functions, specifically in first-year students.

show abstract

Predicting key educational outcomes in academic trajectories: a machine-learning approach

Cited by 73 publications

References 70 publications

Educational data mining: prediction of students' academic performance using machine learning algorithms

Educational data mining: prediction of students' academic performance using machine learning algorithms

A machine learning approximation of the 2015 Portuguese high school student grades: A hybrid approach

Executive function assessment: Adaptation of the Amsterdam executive function inventory using Spanish first-year university students from two knowledge areas

Contact Info

Product

Resources

About