An assessment of random forest technique using simulation study: illustration with infant mortality in Bangladesh

We aimed to assess different machine learning techniques for predicting infant mortality (<1 year) in Bangladesh. The decision tree (DT), random forest (RF), support vector machine (SVM) and logistic regression (LR) approaches were evaluated through accuracy, sensitivity, specificity, precision, F1-score, receiver operating characteristics curve and k-fold cross-validation via simulations. The Boruta algorithm and chi-square ( $$ ) test were used for features selection of infant mortality. Overall, the RF technique (Boruta: accuracy = 0.8890, sensitivity = 0.0480, specificity = 0.9789, precision = 0.1960, F1-score = 0.0771, AUC = 0.6590; $$ : accuracy = 0.8856, sensitivity = 0.0536, specificity = 0.9745, precision = 0.1837, F1-score = 0.0828, AUC = 0.6480) showed higher predictive performance for infant mortality compared to other approaches. Age at first marriage and birth, body mass index (BMI), birth interval, place of residence, religion, administrative division, parents education, occupation of mother, media-exposure, wealth index, gender of child, birth order, children ever born, toilet facility and cooking fuel were potential determinants of infant mortality in Bangladesh. Study findings may help women, stakeholders and policy-makers to take necessary steps for reducing infant mortality by creating awareness, expanding educational programs at community levels and public health interventions.