Table 1.

Hyper parameter grid for the selected model, used as a setting to train the model.

No	Algorithm	Hyper Parameter name	Hyper parameter grid	Best parameter
1	Random forest	n_estimators	[ 100, 500, 1000]	500
		Criterion	[‘gini’, ‘entropy’]	Entropy
		max_depth	[None, 10]	None
		min_samples_split	[5, 10]	5
		min_samples_leaf	[2, 5]	2
		max_features	[‘auto’, ‘sqrt’]	Auto
2	Extreme gradient boosting	n_estimators	[ 100, 500, 1000]	100
		learning_rate	[0.1,0.3, 0.5,0.7, 1.0]	0.5
		max_depth	[None, 10]	None
		Subsample	[0.9, 0.8, 0.7]	0.9
		Gamma	[0, 0.1, 0.5]	0.1
		min_chlid_weight	[1, 3, 5]	3
3	Extra tree	n_estimators	[ 100, 500, 1000]	1000
		Criterion	[‘gini’, ‘entropy’]	Gini
		min_samples_split	[5, 10]	5
		min_samples_leaf	[2, 5]	2
		max_depth	[None, 10]	None
		max_features	[‘auto’, ‘sqrt’]	Auto
4	MLP	Activation Function	[Softmax, relu]	Softmax
		Learning Rate	[0.001, 0.0001, 0.00001]	0.001
		Number of layers	[3, 4, 5]	5
		hidden_layer_sizes	[50,100]	50
		Dropout rate	[0.2, 0.3, 0.4]	0.3
		l2_regs	[0.001, 0.0001]	0.001
		num_dense_layers	[1, 2]	2
		Batch size	[8, 16, 32]	8