Table 4 Algorithm results Algorithm... | Emerald Publishing

Table 4

Algorithm results

Algorithm	Settings	Results
Algorithm	Settings	Training accuracy	Validation accuracy	Precision	Recall	F1-score
Adam ANN	One input layer, one hidden layer and one output layer Input layer with 8 nodes Hidden layer with 16 nodes Output layer with 3 nodes Kernel initialiser = Glorot uniform Activation function = Rectified Linear Unit (RELU) Batch size = 32 Epoch = 100. (Plateau after 40)	0.875	0.855	0.853	0.852	0.851
Random forest	Using GridSearchCV Bootstrap = False Maximum depth = 4 Maximum features = sqrt Minimum samples leaf' = 2 Minimum samples split = 2 Number of estimators = 33	0.842	0.832	0.830	0.866	0.846
SVM	Using RandomSearchCV C = 10 Gamma = 1 Kernel = Radial Basis Function	0.982	0.884	0.883	0.882	0.882
Xgboost	Using GridSearchCV Booster = gbtree Maximum delta step = 0 Maximum depth = 9 Minimum child weight = 1 Number of estimators = 64 Sampling method = uniform	0.999 (overfitting)	0.896	0.917	0.909	0.913
KNN	Using GridSearchCV metric = “euclidean” n_neighbors = 1,000, weights = “distance”	1 (overfitting)	0.750	0.748	0.766	0.719

Algorithm	Settings	Results
Algorithm	Settings	Training accuracy	Validation accuracy	Precision	Recall	F1-score
Adam ANN	One input layer, one hidden layer and one output layerInput layer with 8 nodesHidden layer with 16 nodesOutput layer with 3 nodesKernel initialiser = Glorot uniformActivation function = Rectified Linear Unit (RELU)Batch size = 32Epoch = 100. (Plateau after 40)	0.875	0.855	0.853	0.852	0.851
Random forest	Using GridSearchCVBootstrap = FalseMaximum depth = 4Maximum features = sqrtMinimum samples leaf' = 2Minimum samples split = 2Number of estimators = 33	0.842	0.832	0.830	0.866	0.846
SVM	Using RandomSearchCVC = 10Gamma = 1Kernel = Radial Basis Function	0.982	0.884	0.883	0.882	0.882
Xgboost	Using GridSearchCVBooster = gbtreeMaximum delta step = 0Maximum depth = 9Minimum child weight = 1Number of estimators = 64Sampling method = uniform	0.999(overfitting)	0.896	0.917	0.909	0.913
KNN	Using GridSearchCVmetric = “euclidean” n_neighbors = 1,000, weights = “distance”	1(overfitting)	0.750	0.748	0.766	0.719

Source(s): Authors own work