Food sales prediction model using machine learning techniques

Abstract

Food sales prediction means how to obtain future results of sales of companies. The purpose of this step is to increase the profits of these companies by avoiding spoilage of food products and avoiding buying more quantities than the needs of these companies, which means the accumulation of these products in the warehouses without selling them. Stocked and expired products require a model that guesses the actual future need for these products. In this study, a model for food sales prediction using machine learning algorithms is proposed to achieve two objectives, first: make a comparison between two datasets, one dataset with a high correlation between its features, and another dataset has a low correlation between its features. The second objective is to use several machine learning algorithms for prediction and comparing between these algorithms to find the best three algorithms that give the best prediction. By using the most important metrics such as root mean square error (RMSE) and mean square error (MSE) found the best three algorithms by using the first dataset are support vector machines (SVMs), least absolute shrinkage and selection operator (LASSO), and bagging regressor) and the best three algorithms by using the second dataset are (gradient boosting, random forest regressor, and decision tree).