Skip to main content

Table 2 Summary of results of research seeking degree level prediction

From: Predicting academic success in higher education: literature review and best practices

Ref

Algorithms Used

Model

Sample Size

Best Accuracy

Software

(Hamoud et al., 2018)

J48; REPTree; RT

[C]

161

REPTree-62.3%

WEKA

(Al-barrak & Al-razgan, 2016)

J48

[C]

236

WEKA

(Putpuek et al., 2018)

ID3; C4.5; KNN; NB

[C]

NB - 43.18%

RapidMiner

(Asif et al., 2015)

NB; KNN; NN; DT; RI

[C]

347

NB - 83.65%

RapidMiner

(Oshodi et al., 2018)

LR; SVM

[C][R]

101

SVM − 76.67%

R

(Adekitan & Salau, 2019)

PNN; RF; DT; NB; TE; LR

[C][R]

1841

LR - 89.15%

KNIME-MATLAB

(Asif et al., 2017)

NB; K-NN; RF; NN; DT; RI; X-means

[C] [CC]

210

NB-83.65%

RapidMiner

  1. [C] for classification; [R] for regression; [CC] for clustering; BN Bayes net, DT decision tree, KNN k-nearest neighbors, LR logistic regression, NB naive Bayes, (P)NN (probabilistic) neural network, RB rule based, RI rule induction, RF random forest, RT random tree, NN neural network, TE tree ensemble; −: information not available