Food Sales Prediction Using MLP, RANSAC, and Bagging

Many datasets about food sales, these datasets contain different features depending on the data present. Also, the way these features are correlated differs from one dataset to another. The researchers used several artificial intelligence algorithms and applied them to food sales datasets. Despite the necessary pre-processing and cleaning of the datasets, some of the algorithms used in these studies did not give the desired results. Therefore, this study proposes a model based on two objectives, the first objective is to make a comparison between three different food sales datasets. the second objective is to apply three various Artificial Intelligence algorithms to obtain the best algorithm that gives the highest prediction accuracy with the specified dataset. Some studies used classical machine learning algorithms, some used deep learning algorithms, and others used ensemble techniques. To achieve a comprehensive comparison, one algorithm was chosen from each of the above. To measure the correlation between features used a tool available from the Seaborn library in Python. This tool is called a “Heatmap”. For comparison, used three datasets on which we performed the necessary preprocessing operations, after applying three algorithms, these algorithms are Multilayer perceptron, RANSAC, and Bagging regression. Then used several metrics to measure the accuracy of the algorithm applied to the specified dataset. Finally, identified the best dataset that gives excellent prediction results with these algorithms. The results showed that the first dataset gave ideal accuracy by using the Bagging regression algorithm, unlike the second dataset with medium correlation and the third dataset with weak correlation. This study lays the foundation for subsequent studies and saves them time in terms of choosing the datasets.