Table 3 Performance comparison of the XGBoost predictive model with other models

Random Forest

0.7715 \(\:\pm\:\) 0.0287

0.7714 \(\:\pm\:\) 0.0288

Gradient Boosting

0.7594 \(\:\pm\:\) 0.0215

0.7592 \(\:\pm\:\) 0.0218

Logistic Regression

0.6317 \(\:\pm\:\) 0.0225

0.6266 \(\:\pm\:\) 0.0209

SVM

0.7056 \(\:\pm\:\) 0.0344

0.7023 \(\:\pm\:\) 0.0374

KNN

0.6788 \(\:\pm\:\) 0.0346

0.6706 \(\:\pm\:\) 0.0372

Decision Tree

0.6814 \(\:\pm\:\) 0.0376

0.6812 \(\:\pm\:\) 0.0375

Naive Bayes

0.6371 \(\:\pm\:\) 0.0271

0.6339 \(\:\pm\:\) 0.0288

MLP

0.7030 \(\:\pm\:\) 0.0259

0.7024 \(\:\pm\:\) 0.0265

LightGBM

0.7648 \(\:\pm\:\) 0.0237

0.7645 \(\:\pm\:\) 0.0239

OUR Xgboost

0.7836 \(\:\pm\:\) 0.0229

0.7833 \(\:\pm\:\) 0.0229