A Context-Aware Smart Food Court Recommendation and Ordering System

Abstract

The growing adoption of artificial intelligence in service applications has led to the development of intelligent systems that significantly enhance user experience and operational efficiency. At college dining halls and food courts, conventional ordering methods depend on fixed menus and manual choices, resulting in prolonged decision-making and restricted personalization. This paper presents a Smart Food Recommendation System that provides tailored food suggestions considering user preferences, mood, budget, and past orders to tackle these challenges. The platform utilizes a rule-based recommendation engine in a web-based canteen management system developed with HTML, CSS, JavaScript, Python (Flask), and SQLite. Food products are categorized by mood labels, price categories, and preference features to offer context-sensitive suggestions. Its modular design features user authentication, menu management, recommendation processing, order handling, payment verification, and feedback collection, providing convenience for users and oversight for administrators. By incorporating personalized filtering and budget-conscious suggestions, the system minimizes food selection time, enhances recommendation accuracy, and boosts overall user satisfaction. Experimental implementation in a college dining area shows better efficiency than conventional menu-driven ordering.

Introduction

Choosing suitable meals from many menu options can be difficult for consumers, especially in institutional environments such as college food courts. To address this issue, the Smart Food Recommendation System is proposed to provide personalized meal suggestions using structured filtering techniques and user preferences. The system organizes food items into categories and uses rule-based filtering to generate recommendations based on factors such as mood, dietary preferences (vegetarian/non-vegetarian), and budget. This approach improves decision-making, reduces confusion, and enhances user satisfaction during meal selection.

Traditional food ordering systems usually display static menus without personalization, leaving users to choose items manually. In contrast, the proposed system introduces contextual engagement by using food metadata, user inputs, and order history stored in a database to deliver relevant recommendations. The system also records user behavior and feedback to gradually improve suggestion accuracy.

An administrative module allows managers to control menu items, update prices, track orders, and analyze sales trends through a centralized dashboard. Automation features such as order management, payment verification, and transaction recording enhance operational efficiency and transparency.

Evaluation in a simulated college food court showed that the system reduces decision-making time, improves recommendation relevance, and increases user satisfaction. Although the current design uses simple rule-based logic rather than complex machine learning, it remains efficient, scalable, and easy to maintain.

Future improvements may include integrating AI and machine learning techniques such as collaborative filtering, sentiment analysis for mood detection, natural language processing for conversational food queries, nutritional recommendation features, and cloud-based deployment for broader scalability.

Conclusion

This document showcased the development and execution of an Intelligent Food Suggestion System designed specifically for institutional food court settings. The proposed system enhances traditional menu browsing into an intelligent, personalized experience by combining rule-based contextual filtering with a web-based canteen management platform. The system efficiently merges user preferences, mood factors, budget limits, and order history to produce pertinent food recommendations while ensuring computational ease and scalability. By utilizing modular architecture and centralized administrative oversight, the platform improves operational efficiency and simplifies order processing. Performance assessment shows that contextual recommendation notably shortens decision-making time, enhances user satisfaction, and facilitates effective data-driven management. In contrast to elaborate large-scale recommender systems, the suggested lightweight method provides an efficient and affordable option appropriate for small to medium-sized institutions. Ultimately, the Smart Food Recommendation System connects traditional food ordering systems with AI-enhanced customization. Incorporating contextual intelligence into daily campus dining services demonstrates the real-world effectiveness of artificial intelligence in improving user convenience, operational clarity, and service excellence. The incorporation of advanced machine learning methods in the future could enhance personalization features and develop the system into a scalable intelligent dining ecosystem.

References

[1] F. Rehman, N. Haq, and A. U. R. Khan, “Diet-Right: A Smart Food Recommendation System,” Ajman University, June 2017. DOI: https://doi.org/10.3837/tiis.2017.06.006 [2] M. N. Jasim and A. B. Hamid, “Food Recommendation System Based on Nutritional Needs of Humans and User Preferences,” International Journal of Interactive Mobile Technologies, vol. 6, no. S4, 2021. DOI: https://doi.org/10.53730/ijhs.v6nS4.9031 [3] Z. Patel and H. J. Chokshi, “Food Recommender System: Methods, Challenges, and Future Research Directions,” IJETT, 2025. DOI: https://doi.org/10.14445/22315381/IJETT-V73I5P123 [4] Y. Y. Chow, S. C. Haw, P. Naveen, E. A. Anaam, and H. B. Mahdin, “Food Recommender System: A Review on Techniques, Datasets and Evaluation Metrics,” Journal of Soft Computing and Decision Support Systems, 2023. DOI: https://doi.org/10.33168/JSMS.2023.0510 [5] D. Bianchini, V. De Antonellis, N. De Franceschi, and M. Melchiori, “A Prescription-Based Food Recommendation System,” Computer Standards & Interfaces, vol. 54, pp. 64–76, 2018. DOI: https://doi.org/10.1016/j.csi.2016.10.010 [6] M. Joshikha and C. Khemka, “Food Recommender System Using Content-Based Filtering,” July 2024. DOI: https://doi.org/10.1063/5.0217594 [7] S. Almashjari and H. Ismail, “Intelligent Food Recommendation Framework Based on Social Media Behavioral Data,” 2024. DOI: https://doi.org/10.1145/3660853.3660883 [8] A. El Majjdoi and A. D. Strake, “Integrating Digital Food Nudges and Recommender Systems: Current Status and Future Directions,” IEEE Access, 2025. DOI: https://doi.org/10.1109/ACCESS.2025.3588663 [9] G. Adomavicius and A. Tuzhilin, “Toward the Next Generation of Recommender Systems: A Survey of the State-of-the-Art and Possible Extensions,” IEEE Transactions on Knowledge and Data Engineering, June 2005. DOI: https://doi.org/10.1109/TKDE.2005.99 [10] S. Jha, K. Bhatt, P. Garg, N. Tripathi, and A. K. Yadav, “Food Delivery and Recommendation System,” 2025. Available: https://www.scribd.com/document/827639272/FOOD-RECOMMENDATION-SYSTE11011 [11] R. Akshaya, K. Himalini, and V. Kamalini, “Smart Food Court Ordering System,” International Journal of Research Publication and Reviews, vol. 6, no. 11, pp. 8692–8694, Nov. 2025. Available: https://ijrpr.com/uploads/V6ISSUE11/IJRPR56172.pdf [12] C. Cuento and A. D. Padua, “Enhancing the Overall Customer Experience Through Simulation of Hybrid Ordering System in Fast-Food Restaurants,” Sep. 2025. DOI: https://doi.org/10.1080/29966892.2025.2553764

Copyright

Copyright © 2026 N.L.D. Sri Lasya, K.P.S.S. Valli, K. Vijaya Kumari, B.S. Sandeep, K.M.S. Praveen, K. Sudarshan, B. Narasimha Rao. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.