Skip to main content

Table 4 The prediction performance of different machine learning models for the level of DD in preschool children using EDHS data

From: Improving machine learning models through explainable AI for predicting the level of dietary diversity among Ethiopian preschool children

Model

Accuracy

Recall

Precision

F1-Score

ROC

Decision Tree

83.9%

83.9%

84.3%

84.0%

92.0%

Random Forest

82.2%

82.2%

82.7%

80.3%

91.0%

Gradient Boosting

92.6%

91.6%

91.7%

91.6%

98.0%

Light Gradient Boosting

95.3%

95.3%

95.5%

95.3%

99.0%

CatBoost

92.8%

91.7%

92.1%

91.9%

98.0%

XGBClassifier

83.8%

83.8%

84.3%

84.0%

92.0%