Ml-based Nutritional Analysis And Prediction For Canteen Foods

Abstract

Unhealthy Eating Habits And Lack Of Nutritional Awareness Are Common Among Students In Educational Institutions. Most Canteen Menus Do Not Include Nutritional Information, Leading To Poor Dietary Decisions. The Proposed System, ML-Based Nutritional Analysis And Prediction For Canteen Foods, Introduces A Data-driven Approach To Automatically Estimate Nutrient Values For Campus Food Items Using Machine Learning. Ingredient-level Data From Reliable Sources Such As USDA And Kaggle Indian Food Datasets Are Combined With Campus Menu Recipes To Form A Structured Dataset. The System Applies Multi-Output Random Forest Regression To Predict Key Nutrients — Calories, Protein, Fat, And Carbohydrates — Per Serving. The Model Efficiently Processes Ingredient Inputs And Generates Accurate Nutrient Breakdowns, Helping Students And Diet-consciousindividuals Make Informed Food Choices. This Work Demonstrates How Machine Learning Can Transform Traditional Canteen Services Into Smart, Health-aware Systems, Promoting Balanced Dietary Habits On Campus

Keywords