AI-Based Smart Food Availability Recommendation System Using Machine Learning

We set out to see whether survey evidence and retail inventory data could be combined to recommend an action for each food item. Three classifiers were trained on 800 records and tested on 200, and all of them reached 100% accuracy, precision, recall and F1-score. We kept the Decision Tree as the final model because it is the easiest to interpret. Spoilage chance, days until expiry, stock quantity and daily sales were the most influential features, and the surveys showed that food safety, shelf life, quantity and distance are what donors and receivers value most. Because the scores are perfect, the data is small and some classes are very rare, the system needs to be validated on real data before anyone relies on it. It is meant as an aid for decision-making, and judgements about food safety must stay with trained people.

[1]    V. Suresh, A. N. Jonnalagadda, D. Jagdheesh and M. Balasubramanian, “ZeroHunger: A digital solution for reducing food waste and hunger alleviation,” 2025, doi: 10.2991/978-94-6463-866-0_67. [2]    V. Dhanokar et al., “Annapurna: An intelligent food donation system with AI-based receiver recommendation,” 2026, doi: 10.51583/IJLTEMAS.2026.150500008. [3]    B. Bhargavi et al., “AI based food donation and distribution system,” 2026, doi: 10.17148/IJARCCE.2026.154313. [4]    T.-S. Uen and L. F. Rodríguez, “Geospatial analytics and machine learning for forecasting county-level food waste in U.S. retail markets,” Resources, Conservation and Recycling, vol. 231, Art. no. 108906, 2026, doi: 10.1016/j.resconrec.2026.108906. [5]    Z. Said et al., “Intelligent approaches for sustainable management and valorisation of food waste,” Bioresource Technology, vol. 377, Art. no. 128952, 2023, doi: 10.1016/j.biortech.2023.128952. [6]    M. Rashvand, Y. Ren, D.-W. Sun, J. Senge, C. Krupitzer et al., “Artificial intelligence for prediction of shelf-life of various food products: Recent advances and ongoing challenges,” Trends in Food Science & Technology, vol. 159, Art. no. 104989, 2025, doi: 10.1016/j.tifs.2025.104989. [7]    C. Trattner and D. Elsweiler, “Food recommender systems: Important contributions, challenges and future research directions,” 2017. [8]    W. Min, S. Jiang and R. Jain, “Food recommendation: Framework, existing solutions and challenges,” 2019. [9]    K. M. Hudak, E. Friedman, J. Johnson and S. E. Benjamin-Neelon, “Food bank donations in the United States: A landscape review of federal policies,” Nutrients, vol. 12, no. 12, Art. no. 3764, 2020, doi: 10.3390/nu12123764. [10]  F. Pedregosa, G. Varoquaux, A. Gramfort et al., “Scikit-learn: Machine learning in Python,” J. Mach. Learn. Res., vol. 12, pp. 2825–2830, 2011.