Table 3 Model performance comparison before SMOTE.

From: Predicting car accident severity in Northwest Ethiopia: a machine learning approach leveraging driver, environmental, and road conditions

Model

Accuracy

Precision

Recall

F1 Score

ROC AUC

Random Forest

0.77

0.81

0.75

0.78

0.86

XGBoost

0.76

0.78

0.78

0.78

0.85

LightGBM

0.77

0.77

0.82

0.79

0.85

KNN

0.71

0.85

0.55

0.67

0.82

Gradient Boosting

0.76

0.75

0.82

0.78

0.81

Neural Network

0.7

0.74

0.69

0.71

0.74

SVM

0.68

0.73

0.64

0.68

0.73

Logistic Regression

0.64

0.68

0.61

0.64

0.67

Naive Bayes

0.63

0.67

0.61

0.64

0.67

Decision Tree

0.66

0.71

0.62

0.66

0.66