Effective Recommendation of Nutritious Food Using Random Forest Classifier in Comparison with Multi‐Layer Perceptron Classifier Algorithm

The aim of the study is to predict the nutrient-dense food categories using the Novel Random Forest Classifier in comparison with Multi-Layer Perceptron Classifier. Novel Random Forest Classifier and Multi-Layer Perceptron Classifier are the two algorithms considered for the current research, each with a number of iterations. Twenty are calculated using clincalc software with a G-power value of 80% and 95% confidence level. The dataset for the present work includes 5,250 values linked to the foods, ingredients, and cuisines; the factors considered are reviews, healthy food, snacks, and fast food. The accuracy of Novel Random Forest Classifier is 79.70% over Multi-Layer Perceptron Classifier with accuracy of 72.27% with a significance value of 0.01 (Independent Sample T-test p