Modelling, prediction and classification of student academic performance using artificial neural networks

Lau, Ethan; Sun, Li; Yang, Qing

doi:10.1007/s42452-019-0884-7

Cited by 136 publications

(59 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…11. Four data mining algorithms; the Classification Tree, the Neural Network [44], the Naïve Bayes and the Random Forest algorithms were applied to evaluate the predictive capabilities of the student features considered. 70% of the data population was randomly selected using stratified sampling for training the model, while the remaining 30% was deployed for performance evaluation, and the training-test sequence was repeated ten times.…”

Section: Educational Data Mining Using Orange Applicationmentioning

confidence: 99%

Toward an improved learning process: the relevance of ethnicity to data mining prediction of students’ performance

Adekitan

Salau

2019

SN Appl. Sci.

View full text Add to dashboard Cite

The ability to predict failure is an advantageous educational tool that can be effectively used to counsel student, and this may also be used as a tool for developing, and channelling adequate academic interventions toward preventing failure and dropout tendencies. Students are generally admitted based on their evaluated academic potentials as measured using their admission criteria scores. This study seeks to identify the relationship, if any, between the admission criteria scores and the graduation grades, and to examine the influence of ethnicity using the geopolitical zone of origin of the student on the predictive accuracy of the models developed using a Nigerian University as a case study. Data mining analyses were carried out using four classifiers on the Orange Software, and the results were verified with multiple regression analysis. The maximum classification accuracy observed is 53.2% which indicates that the pre-admission scores alone are insufficient for predicting the graduation result of students but it may serve as a useful guide. By applying over-sampling technique, the accuracy increased to 79.8%. The results establish that the ethnic background of the student is statistically insignificant in predicting their graduation results. Hence, the use of ethnicity in admission processes is therefore not ideal.

show abstract

Section: Educational Data Mining Using Orange Applicationmentioning

confidence: 99%

Toward an improved learning process: the relevance of ethnicity to data mining prediction of students’ performance

Adekitan

Salau

2019

SN Appl. Sci.

View full text Add to dashboard Cite

show abstract

“…Machine learning approaches as artificial neural networks (ANN) allow the use of large volumes of data and non-linear relationships between predictors, and they have been shown to be very effective to classify various educational outcomes (e.g., Abu Naser 2012;Ahmad & Shahzadi 2018;Kanakana and Olanrewaju 2011;Musso et al 2012Musso et al , 2013Lau, Sun & Yang 2019). Other advantages of ANN are that they do not require the fulfillment of assumptions of normality, linearity, and completeness (Kent 2009, Garson 1998.…”

Section: Introductionmentioning

confidence: 99%

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

2020

View full text Add to dashboard Cite

Predicting and understanding different key outcomes in a student’s academic trajectory such as grade point average, academic retention, and degree completion would allow targeted intervention programs in higher education. Most of the predictive models developed for those key outcomes have been based on traditional methodological approaches. However, these models assume linear relationships between variables and do not always yield accurate predictive classifications. On the other hand, the use of machine-learning approaches such as artificial neural networks has been very effective in the classification of various educational outcomes, overcoming the limitations of traditional methodological approaches. In this study, multilayer perceptron artificial neural network models, with a backpropagation algorithm, were developed to classify levels of grade point average, academic retention, and degree completion outcomes in a sample of 655 students from a private university. Findings showed a high level of accuracy for all the classifications. Among the predictors, learning strategies had the greatest contribution for the prediction of grade point average. Coping strategies were the best predictors for degree completion, and background information had the largest predictive weight for the identification of students who will drop out or not from the university programs.

show abstract

“…Through estimation on data captured from three two-week courses hosted through our delivery platforms, make three key observations: (i) behavioral data contains signals predictive of learning outcomes in short-courses (with classifiers achieving AUCs ≥ 0:8 after the two weeks), (ii) early detection is possible within the first week (AUCs ≥ 0:7 with the first week of data), and (iii) the content features have an "earliest" detection capability, while the SLN features become the more predictive set over time as the network matures. [9] proposed an approach that combines traditional statistical analysis with neural network modeling/prediction of student results Traditional statistical evaluations are used to determine the variables that are likely to influence the students' results. The neural network is represented by 11 input variables, two hidden neuron layers, and one output layer.…”

Section: Ghorbani R and Ghousi R (2020) [5]mentioning

confidence: 99%

Study Of Students’ Performance Prediction Models Using Machine Learning

Viswanathan¹

2021

TURCOMAT

View full text Add to dashboard Cite

Educational Data Mining (EDM) is a novel concept associated with developing methods for exploring the specific types of data produced by educational settings and using those approaches to effectively understand students and the environments in which they learn. Prediction attempts to shape trends that will allow it to predict results or learning outcomes based on available data. Predicting student success has become an appealing challenge for researchers. They develop an understandable and efficient model using supervised and unsupervised EDM techniques. This assists decision-makers in improving student performance. The task of deciding the best model leads to the emergence of various techniques from both EDM techniques. The numerous research models used to solve the problem of student success prediction using educational data mining are discussed in this paper. The primary purpose of this paper is to explain the methodology for implementing the proposed solution for student performance prediction, as well as to present the findings of a study aimed at evaluating the performance of various data mining classification algorithms on the given dataset in order to assess their potential usefulness for achieving the goal and objectives.

show abstract

Modelling, prediction and classification of student academic performance using artificial neural networks

Cited by 136 publications

References 14 publications

Toward an improved learning process: the relevance of ethnicity to data mining prediction of students’ performance

Toward an improved learning process: the relevance of ethnicity to data mining prediction of students’ performance

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

Study Of Students’ Performance Prediction Models Using Machine Learning

Contact Info

Product

Resources

About