Research Article
EMT: Ensemble Meta-Based Tree Model for Predicting Student Performance
Table 4
Comparison between five groups of classification algorithms (accuracy and F-measure values).
| Algorithm’s family | Algorithm name | Dataset | Accuracy | F-measure |
| Rules | ConjunctiveRule | 0.633 | 0.533 | DecisionTable | 0.850 | 0.849 | DTNB | 0.855 | 0.854 | FURIA | 0.888 | 0.887 | JRip | 0.873 | 0.872 | LAC | 0.780 | 0.781 | MODLEM | 0.873 | 0.872 | MultiobjectiveEvolutionaryFuzzy | 0.628 | 0.624 | NNge | 0.830 | 0.831 | OLM | 0.668 | 0.661 | OneR | 0.695 | 0.692 | PART | 0.918 | 0.918 | Ridor | 0.875 | 0.874 | RoughSet | 0.870 | 0.869 | ZeroR | 0.433 | 0.261 |
| Bayes | A1DE | 0.880 | 0.880 | A2DE | 0.895 | 0.895 | BayesNet | 0.850 | 0.849 | NaiveBayes | 0.773 | 0.769 |
| Function | LibLINEAR | 0.690 | 0.688 | LibSVM | 0.540 | 0.470 | MLPClassifier | 0.893 | 0.892 | Multilayer perceptron | 0.910 | 0.910 | MultilayerPerceptronCS | 0.910 | 0.910 | RBFClassifier | 0.853 | 0.853 | SMO | 0.870 | 0.870 |
| Lazy | IB1 | 0.838 | 0.837 | IBK | 0.838 | 0.837 | IBKLG | 0.838 | 0.837 | KStar | 0.863 | 0.862 | LocalKnn | 0.928 | 0.927 | RseslibKnn | 0.928 | 0.927 | Trees | BFTree | 0.905 | 0.905 | CDT | 0.903 | 0.902 | DecisionStump | 0.558 | 0.406 | ForestPA | 0.910 | 0.910 | FT | 0.883 | 0.883 | HoeffdingTree | 0.773 | 0.769 | J48 | 0.943 | 0.943 | J48Consolidated | 0.940 | 0.940 | LADTree | 0.900 | 0.900 | LMT | 0.933 | 0.932 | NBTree | 0.925 | 0.925 | RandomForest | 0.935 | 0.935 | RandomTree | 0.828 | 0.827 | REPTree | 0.893 | 0.893 | SimpleCart | 0.893 | 0.892 |
|
|