Predicting Flight Delays with Machine Learning: A Case Study from Saudi Arabian Airlines

Table 3

Comparison of performance results of different ML-based models on our test dataset for our classification task.

	CatBoost	XGBoost	LightGBM	MLP	Random forests
Accuracy	76	73.1	73.2	72.5	71.3
Recall	74.8	71.6	71.7	71.1	69.8
Precision	75.6	72.6	72.6	71.8	70.6
-score	75.1	71.9	72	71.4	70.1
AUC	0.74	0.72	0.72	0.71	0.7