{"title":"Development of an AI-based restaurant menu demand prediction model utilizing sales and meteorological data","authors":"Sangoh Kim","doi":"10.1007/s10068-025-01956-2","DOIUrl":null,"url":null,"abstract":"<div><p>Accurate demand forecasting in the restaurant industry is critical for optimizing inventory management, minimizing food waste, and enhancing operational efficiency. This study developed an AI-based system that predicts menu-specific daily sales using historical sales and meteorological data collected from 2021 to 2023. Approximately 384 menu items were individually modeled using deep neural networks configured for multi-class classification. The system achieved strong predictive performance with a mean Pearson correlation coefficient of 0.7945. Additionally, flexible visualization options were implemented to sort predictions by expected or actual sales volumes. The results demonstrate the feasibility of AI-driven demand prediction systems and their potential to transform food service operations toward greater sustainability and efficiency.</p></div>","PeriodicalId":566,"journal":{"name":"Food Science and Biotechnology","volume":"34 15","pages":"3597 - 3606"},"PeriodicalIF":3.1000,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Food Science and Biotechnology","FirstCategoryId":"97","ListUrlMain":"https://link.springer.com/article/10.1007/s10068-025-01956-2","RegionNum":3,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"FOOD SCIENCE & TECHNOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Accurate demand forecasting in the restaurant industry is critical for optimizing inventory management, minimizing food waste, and enhancing operational efficiency. This study developed an AI-based system that predicts menu-specific daily sales using historical sales and meteorological data collected from 2021 to 2023. Approximately 384 menu items were individually modeled using deep neural networks configured for multi-class classification. The system achieved strong predictive performance with a mean Pearson correlation coefficient of 0.7945. Additionally, flexible visualization options were implemented to sort predictions by expected or actual sales volumes. The results demonstrate the feasibility of AI-driven demand prediction systems and their potential to transform food service operations toward greater sustainability and efficiency.
期刊介绍：
The FSB journal covers food chemistry and analysis for compositional and physiological activity changes, food hygiene and toxicology, food microbiology and biotechnology, and food engineering involved in during and after food processing through physical, chemical, and biological ways. Consumer perception and sensory evaluation on processed foods are accepted only when they are relevant to the laboratory research work. As a general rule, manuscripts dealing with analysis and efficacy of extracts from natural resources prior to the processing or without any related food processing may not be considered within the scope of the journal. The FSB journal does not deal with only local interest and a lack of significant scientific merit. The main scope of our journal is seeking for human health and wellness through constructive works and new findings in food science and biotechnology field.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
