Decision trees achieve competitive accuracy with black-box models (LR, RF, SVM), which performed slightly better but lack interpretability¶

Claim · All claims
Evidence · 1 study · associational r2 · q2
Currency · newest study 2025 · not yet checked against its sources · not reviewed by a person · recheck by 2028: tool and model accuracy changes quickly

Subclaims¶

q2 i? LR, RF and SVM performed slightly better than DTs, with SVM best at 83.9-94.4% accuracy, but SVM and RF are black-box and SVM and LR were slow to train. → Vincent Zhang 2025

Evidence¶

Vincent Zhang 2025¶

Vincent Zhang, Bryn Jeffries, Irena Koprinska. (2025). A Machine Learning Approach for Predicting Student Progress in Online Programming Education. Int J Artif Intell Educ. https://doi.org/10.1007/s40593-025-00510-9

q2 · i? · associational · r2

Comparison reported in the Results section across the same four-course module-level evaluation: DTs versus Logistic Regression, Random Forest and Support Vector Machine, all with Weka default settings. The article reports SVM "achieved 83.9-94.4 accuracy" while noting the interpretability and training-speed trade-off.

"The machine learning methods used for comparison - LR, RF and SVM, performed slightly better than DTs, e.g. the best performing method SVM achieved 83.9-94.4 accuracy, 0.84-0.94 precision, 0.84-0.94 recall and 0.87-0.94 F1 score. These methods however lack interpretability, and SVM and LR were also slow to train which limits their applicability for our case study."

Discussion¶

Related Claims¶

• A support vector machine classifier outperformed decision tree and random forest models in predicting cognitive engagement levels of online discussion posts — related
• Random forest algorithms yielded the best classification performance in K–8 MMLA studies comparing multiple machine learning models — reports the opposite
• A random forest classified flagged versus non-flagged word problems with the best accuracy of five tested models (AUC = 0.75) — reports the opposite
• Simple classifiers (Logistic Regression, Naive Bayes) outperformed tree-based models on this small dataset — related
• All three trained classifiers outperformed the zero-rule baseline (28.4% accuracy) for classifying cognitive engagement in discussion posts — related
• Decision tree classifiers trained on slide interaction features predict end-of-module outcomes with high accuracy across four K-12 programming courses — related
• Machine learning methods outperformed logistic regression in classification accuracy across reviewed studies — reports the opposite
• Logistic regression performs poorly (mean accuracy 0.4243) and SVM moderately (0.7374) on physiological exam-outcome prediction — related
• Shallow machine learning with SMOTE oversampling and Qwen3 embeddings achieves the best overall reflection-classification performance (0.7176) on Hungarian essays — related
• Baseline LR and XGBoost models achieve comparable predictive performance on OULAD, with XGBoost slightly higher AUC-ROC — related
• AI systems relying on black-box models should not be used for high-stakes applications — related
• An LSTM-based strategy temporal analytics framework outperforms random forest, SVM, and majority-class baselines for stealth assessment predictive accuracy — reports the opposite
• SVM-based regressors outperformed other regressors in the ETF price-delta forecasting benchmark — related
• CFS and GR feature selection shrink decision trees to 3.2-4.7 leaf nodes without degrading predictive performance — related
• CatBoost achieved the best classification performance among tested algorithms for predicting course completion risk (F-measure .77, accuracy 78%, AUC .87) — related
• Boosting models (XGBoost) achieved the highest predictive accuracy among the compared ML models, while logistic regression showed the lowest — reports the opposite