Analysis of Indian Food Based on Machine learning Classification Models

Abstract

For human life, Food is highly necessary and essential for human to live the life. The objective of the current study is to characterise, classify and compare the food consumption patterns of many Indian food diets such as non-vegetarian and vegetarian. Given data about different Indian dishes, we try to predict here the dish is vegetarian or not. To get the best predictive model, this study is conducted with the comparison of Decision Tree, K-Nearest Neighbor (KNN), Support Vector Machine (SVM) and Random Forest algorithms. In this study, the concept and implementation of all these four models be made for prediction of Indian food. For training and testing the models, Indian food dataset is used that contains, in total 255 records to fit with all these four models. In short, the classification and prediction of Decision tree and KNN model provides less performance than the other models used here. However, the Random Forest model was generally more accurate than SVM, KNN and Decision Tree model, which have got from the simulation.