Enhancing Food Quality Assurance: Machine Learning Models for Adulteration Detection in Edible Oils

Abstract

Adulteration in edible oil poses a significant threat to public health, leading to severe economic and health implications. The conventional methods for detecting adulteration are often time-consuming and require sophisticated instruments. This study explores the potential of machine learning (ML) techniques to identify adulteration in edible oils effectively. By leveraging a dataset of chemical properties and adulteration markers, various machine learning algorithms were applied and evaluated to ensure food safety and quality. The proposed methodology demonstrated high accuracy and efficiency, indicating the feasibility of ML as a reliable tool for quality assurance in the edible oil industry.