“Machine Learning-Based Food Edibility Prediction Using Neural Networks”

Safety and the edibility of products is a must in the food industry. This research paper introduces a machine learning method for predicting whether food products can be eaten or not. A neural network model was created using various characteristics of the dataset including shelf life, manufacture date, optimum storage temperature and product type (solid, liquid or gas) to predict the edibility of a given item. The performance of the model was measured using accuracy, Mean Squared Error (MSE), and R-squared (R2). These findings demonstrate that neural networks are effective in classification tasks as they offer dependable means of forecasting if food is unsafe to eat.[1] Traditional methods have received a significant boost by this approach since it allows faster scalable automated predictions that could be integrated into larger food safety systems