Bean Guru is an AI-driven Coffee Recommendation Web Application
Keywords:
Bean guru, Coffee recommendation, Facial emotion, Mongodb atlas, Product recommendation, Web application, Zodiac signAbstract
Bean Guru is an AI-driven coffee recommendation web application designed to deliver personalized coffee suggestions based on user taste preferences, origin choices, roast profiles, and behavioral inputs. The primary objective of this paper is to enhance the user experience in coffee discovery by leveraging intelligent recommendation algorithms and a seamless digital interface. Bean Guru empowers both casual coffee drinkers and enthusiasts to explore blends aligned with their unique flavor profiles.
The application utilizes modern web development technologies including React- based frontend for a dynamic user interface and a Python-based backend built with Flask, integrating machine learning models for recommendation logic. MongoDB Atlas serves as the NoSQL cloud database for storing user preferences and product metadata. The system incorporates user authentication, preference based filtering, and dynamic suggestions through collaborative and content-based filtering techniques.
References
Z. Dinku, "React.js vs. Next.js," Theseus, 2022. Available: https://www.theseus.fi/bitstream/handle/10024/750122/Dinku_Zerihun.pdf
A. Savva, V. Stylianou, K. Kyriacou, and F. Domenach, "Recognizing student facial expressions: A web application," in Proc. 2018 IEEE Global Engineering Education Conf. (EDUCON), Santa Cruz de Tenerife, Spain, Apr. 2018, pp. 1459-1462, doi: https://doi.org/10.1109/EDUCON.2018.8363404
K., Banker, “MongoDB in Action, 2ed: Covers MongoDB Version 3.0,” Wileyindia.com, 2025. https://www.wileyindia.com/mongodb-in-action-2ed-covers-mongodb-version-3-0.html.
J. S. Filippini, J. Varona, and C. Manresa-Yee, "Real-time analysis of facial expressions for mood estimation," Applied Sciences, vol. 14, no. 14, p. 6173, Jul. 2024. Doi: https://doi.org/10.3390/app14146173
S. Chakrabarty, A. Bhattacharya, M. R. Islam, and H. Kumar, “Online Music Recommendations Using User’s Zodiac Sign,” Lecture notes in networks and systems, pp. 327–337, Nov. 2021, doi: https://doi.org/10.1007/978-981-16-4244-9_27.
C. Sompong, A. Kaiburt, P. Penjamuk, A. Supan, T. Boonphiohat, and P. Kunmee, "Multi-factor authentication for web applications using JWT and face embedding-based recognition," in Proc. 2025 IEEE Int. Conf. Cybern. Innov. (ICCI), Apr. 2025, pp. 1-6. doi: https://doi.org/10.1109/ICCI64209.2025.10987510
D. Kuivalainen, "Web application development," Theseus, 2021. Available: https://www.theseus.fi/handle/10024/502093
R. Singh, A. Gehlot, and A. Joshi, “Study on Facial Recognition to Detect Mood and Suggest Songs,” 2022 International Interdisciplinary Humanitarian Conference for Sustainability (IIHC), pp. 1078–1084, Nov. 2022, doi: https://doi.org/10.1109/iihc55949.2022.10060265.
E. Yildirim, F. P. Akbulut, and C. Catal, “Analysis of facial emotion expression in eating occasions using deep learning,” Multimedia Tools and Applications, Mar. 2023, doi: https://doi.org/10.1007/s11042-023-15008-6.
A. Bosch, “The Cycle of the Zodiac Signs: Archetypes Rooted in Reality - Ebook - Annemiek Bosch -Storytel International,” www.storytel.com, 2022. https://www.storytel.com/tv/books/the-cycle-of-the-zodiac-signs-archetypes-rooted-in-reality-2150988.
