Food fraud detection using explainable artificial intelligence

Recently, the global food supply chain has become increasingly complex, and its scalability grown. From farm to fork, performance of food-producing systems is influenced by significant changes in environment, population economy. These may cause an increase fraud safety hazards hence, harm human health. Adopting artificial intelligence (AI) technology one strategy reduce these hazards. Although use AI been rising numerous industries, such as precision nutrition, self-driving cars, agriculture, medicine safety, much what do a black box due poor explainability. This study covers cases risk prediction using explainable (XAI) techniques, LIME, SHAP WIT. We aimed interpret predictions machine learning model with aid technologies. The case was performed on dataset adulteration/fraud notifications retrieved from Rapid Alert System for Food Feed system economically motivated adulteration database. A deep built based this XAI tools have investigated proposed model. Both features shortcomings current area presented.