| | Reference | DL model architecture | Baseline ML model architecture | Evaluation method | Performance |
| | Guo et al. [31] | Student performance prediction network (SPPN) based on the sparse autoencoder | Naïve Bayes, MLP, SVM | Accuracy | Greater | | Akram et al. [32] | LSTM | SVM, RF, majority class | Accuracy, precision, recall, F1 | Greater | | Fok et al. [33] | Deep neural networks | DT, association rules | Accuracy | Greater | | Abhinav et al. [34] | MLP | K-NN, SVD | RMSE, MAE | Greater | | Amazona and Hernandez [35] | ANN | DT, Naïve Bayes | Accuracy | Greater | | Alvarado et al. [36] | WE | N-grams | Precision, recall, F-measure | Equal | | Kim et al. [37] | GritNet, bidirectional long short-term memory (BLSTM) | Standard logistic regression | Performance | Greater | | Fei and Yeung et al. [22] | RNN, LSTM | SVM, LogReg, IOHMM | Accuracy | Greater | | Samuel-Soma et al. [38] | Ensemble techniques | NB, DT, K-NN, disc, PWC | Accuracy, performance | Greater | | Alam et al. [39] | Artificial neural network | Random forest, Chi2 | Classification, accuracy | Equal | | Khajah et al. [40] | LSTM | BKT | Accuracy | Equal | | Ma et al. [41] | DNN | DT, SVM | Prediction, accuracy | Lesser | | Lalwani and Agrawal et al. [42] | LSTM | PFA, BKT | Accuracy | Equal | | El Fouki and Aknin [43] | DNN | PCA | Prediction | — | | Abidi et al. [44] | DL | Generalized linear model (GLM), logistic regression (LR), decision tree (DT), random forest (RF), and gradient boosted trees (XGBoost) | Learners’ confusion prediction | Greater for RF, GLM, XGBoost, and DL | | Hadullo et al. [45] | MLP | — | Performance prediction factors | — | | Wang et al. [46] | CNN, RNN | SVM, LogReg, DT, AdaBoost, GTB, RF, GNB | Accuracy, precision, recall, F-measure | Equal | | Ndukwe et al. [47] | DNN | — | Classification | — | | Whitehill et al. [48] | FNN | — | Accuracy | — | | Chai et al. [49] | ANN | — | Accuracy | Greater | | Yeung and Yeung [50] | LSTM | — | Accuracy | — | | Sun et al. [51] | CNN | ANN | Prediction, feature reconstruction | Greater | | Tanuar et al. [52] | ANN | Linear model, DT | Accuracy | Greater | | Yang et al. [53] | LSTM | — | MSE | — | | Dyuti Islam [54] | MLP | RF, SVM | Accuracy, precision, recall, F-measure | Greater | | Wang et al. [55] | Convolutional GRU | RF, SVM, BPNN, RNN, LSTM | Accuracy, F1-score | Greater | | Saa et al. [56] | NN | RF | Prediction accuracy | Lesser | | Adam et al. [57] | LSTM | — | — | — | | Sharma et al. [58] | CNN, AlexNet, VGG16, LSTM | SVM, HMM | Accuracy | Greater |
|
|
