Artificial Intelligence-Based Decision Support System for Personalized Cosmetic Product Recommendation Using Multisource Data

Jiayue Liu; Jiarui Shen

doi:10.56294/dm20261403

Authors

Jiayue Liu School of Art and Designs, Changsha University of Science and Technology, Changsha, Hunan 410114, China Author https://orcid.org/0009-0004-2909-1804
Jiarui Shen Shenzhen Dibo Enterprise Risk Management Technology Co., Ltd, Shenzhen, Guangdong, 518000 Author https://orcid.org/0009-0000-6715-2517

DOI:

https://doi.org/10.56294/dm20261403

Keywords:

Artificial intelligence, Decision support system, Personalized cosmetic recommendation, Multisource data fusion, Attention-based deep learning, Reinforcement learning

Abstract

Introduction: The increased consumer demand for specific cosmetic products has exposed the limitations of standard recommendation systems that fail to account for individual skin characteristics and contextual circumstances.
Methods: This research introduces an artificial intelligence-driven decision support system for specific cosmetic product recommendations utilizing multisource data, focusing on an innovative Multisource Adaptive Fusion and Attention-Based Recommendation (MAFAR) methodology. The proposed approach combines heterogeneous data, including user demographics, specific skin type and condition attributes, lifestyle and dietary behaviors, environmental conditions such as temperature, humidity, and pollution, cosmetic product ingredient formulations, and historical user interactions. At the feature level, structured data are fused using a simple representation, while an attention-based deep neural network dynamically assigns relevance weights to each data source, providing context-aware and highly specific ideas.
Results: Unstructured data from user reviews and expert comments are processed using natural language processing techniques to extract sentiment, ingredient preferences and adverse response indicators which are incorporated into the recommendation system. To address the dynamic nature of skin conditions and user preferences, a reinforcement learning module is implemented to continuously update recommendation policies based on real-time user feedback.
Conclusions: Numerous studies conducted on a comprehensive multisource cosmetic dataset reveal that the proposed MAFAR technique greatly outperforms standard content-based, collaborative filtering, and hybrid recommendation systems in terms of precision, recall, F1-score, and user satisfaction. Moreover, the decision support system gives interpretable suggestions by detecting influential skin features and crucial substances while promoting transparency and expert validation.

References

1. Chowdary R, Tharun J, Sivaiah G, Raveena S, Surendran R. Deep learning-based hybrid recommendation system for safe approach to curated cosmetics. In: 2025 3rd International Conference on Intelligent Data Communication Technologies and Internet of Things (IDCIoT); 2025 Feb; pp. 2103–2110. IEEE.

2. Eyeberdiyeva A, Gulberdiyeva Y. Building a personalized cosmetics platform for enhanced customer experience. Innovatsionnaya Nauka. 2024;(12-2-1):39–41.

3. Vinutha, M., Dayananda, R.B. and Kamath, A., 2024, June. Personalized Skincare Product Recommendation System Using Content-Based Machine Learning. In 2023 4th International Conference on Intelligent Technologies (CONIT) (pp. 1-6). IEEE.

4. Zhang, D., Li, H., Shi, J., Shen, Y., Zhu, L., Chen, N., Wei, Z., Lv, J., Chen, Y. and Hao, F., 2024. Advancements in acne detection: application of the CenterNet network in smart dermatology. Frontiers in Medicine, 11, p.1344314.

5. Ramrakhiani N, Kalbande D. A comprehensive review of AI-powered skincare product recommendation systems: from data collection to user experience. E-Learning Digit Media. 2024;20427530241304073.

6. Khan REH, Singh K. AI-driven personalized skincare: enhancing skin analysis and product recommendation systems. J Sci Innov Adv Res (JSIAR). 2025;1(2):178–84.

7. Anbalagan NK, Senthilkumar HS, Sakthivel JV, Vadivel K. Vision transformer powered cosmetic prediction recommendation system. In: AIP Conf Proc. 2025 Apr;3279(1):020033. AIP Publishing LLC.

8. Junaidi NFA, Safar NZM, Abdullah N, Kamaludin H. A personalized web cosmetic recommendation system based on skin type. Appl Inf Technol Comput Sci. 2021;2(1):225–34.

9. Perumal I, Kalaivani P, Naveenkumar A, Saran V, Sriram K, Suruthi N. AI-driven personalized skincare recommendations. In: 2025 International Conference on Electronics and Renewable Systems (ICEARS); 2025 Feb; pp. 1086–91. IEEE.

10. Sindhu A, Suresh A, Shaila SG, Bindu B, Akshaya B, Priyanka P. Personalized skincare recommender system using deep learning. In: 2025 3rd International Conference on Advancements in Electrical, Electronics, Communication, Computing and Automation (ICAECA); 2025 Apr; pp. 1–6. IEEE.

11. Yadav A, Khan REH, Singh K. YOLO-based detection of skin anomalies with AI recommendation engine for personalized skincare. J Sci Innov Adv Res (JSIAR). 2025;1(2):216–21.

12. Posamma K, Murthy BS. Skin care product recommendation using skin images. Int J Manag Res Rev. 2025;15(2s):320–6.

13. Sianturi ARN, Kusumadewi A, Lucky H. Skincare recommendation system based on user’s skin characteristics similarity using collaborative filtering approach. In: 2024 IEEE 2nd International Conference on Electrical Engineering, Computer and Information Technology (ICEECIT); 2024 Nov; pp. 72–7. IEEE.

14. Prastiningtyas DA, Purwiantono GS, Purwiantono FE, Aditya A. Enhancing consumer decision-making in skincare: implementation of the VIKOR method for product recommendation systems. Teknika. 2025;14(2):172–80.

15. Singh S, Mali H, Thakur V, Lovalekar S. HairVise: a machine learning, augmented reality and artificial intelligence integrated personalized hair care recommendation framework. In: 2024 8th International Conference on Inventive Systems and Control (ICISC); 2024 Jul; pp. 288–94. IEEE.

16. Perera PRH, Soysa ESS, De Silva HRS, Tavarayan ARP, Gamage MP, Weerasinghe KMLP. Virtual makeover and makeup recommendation based on personal trait analysis. In: 2021 3rd International Conference on Advancements in Computing (ICAC); 2021 Dec; pp. 288–93. IEEE.

17. Krishnan J, Ranjith R, Vijayakumar K. Cosmetic products customisation and customer segmentation. In: 2023 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI); 2023 May; pp. 1–11. IEEE.

18. Kothari A, Shah D, Soni T, Dhage S. Cosmetic skin type classification using CNN with product recommendation. In: 2021 12th International Conference on Computing Communication and Networking Technologies (ICCCNT); 2021 Jul; pp. 1–6. IEEE.

19. Sylvagno GS, Rochadiani TH. Skincare recommendation system based on facial skin type with real-time weather integration. J Sist Inf Komput (Sisfokom). 2025;14(2):230–7.

20. Lin TY, Chan HT, Hsia CH, Lai CF. Facial skincare products’ recommendation with computer vision technologies. Electronics. 2022;11(1):143.

21. Bhavana DE, Gopalkrishna C, Harisha S, Kaushik M. Artificial intelligence-based smart cosmetics suggestion system based on skin condition. In: 2024 Second International Conference on Advances in Information Technology (ICAIT); 2024 Jul; Vol. 1, pp. 1–6. IEEE.

22. Daram L, Pullakhandam G, Godari N, Shobarani S. Virtual glamour: AI-enhanced makeup recommendations and trials. In: 2024 Second International Conference on Inventive Computing and Informatics (ICICI); 2024 Jun; pp. 206–13. IEEE.

23. Adawiyah SR, Purwandari B, Eitiveni I, Purwaningsih EH. The influence of AI and AR technology in personalized recommendations on customer usage intention: a case study of cosmetic products on Shopee. Appl Sci. 2024;14(13):5786.

24. Chouhan R, Barde S. A review on cosmetic product recommendation using deep learning. In: 2024 4th International Conference on Soft Computing for Security Applications (ICSCSA); 2024 Sep; pp. 1–8. IEEE.

25. Lee J, Yoon H, Kim S, Lee C, Lee J, Yoo S. Deep learning-based skin care product recommendation: a focus on cosmetic ingredient analysis and facial skin conditions. J Cosmet Dermatol. 2024;23(6):2066–77.

26. Vinutha M, Dayananda RB, Kamath A. Personalized skincare product recommendation system using content-based machine learning. In: 2023 4th International Conference on Intelligent Technologies (CONIT); 2024 Jun; pp. 1–6. IEEE.

27. Jannatin AA, Ratnasari CI. Personalized skincare recommendation system based on ontology and user preferences. bit-Tech. 2025;8(1):1109–19.

28. Firdaus SA, Nurmuthia LD, Imtiyaz R, Gunawan AAS, Setiawan KE. Cosmetics recommendation system based on ingredients using cosine similarity. In: 2024 International Conference on Data Science and Its Applications (ICoDSA); 2024 Jul; pp. 352–7. IEEE.

29. Hanchinal TK, Bhavani VD, Mindolli VB. Intelligent beauty product recommendation using deep learning. In: 2024 1st International Conference on Cognitive, Green and Ubiquitous Computing (IC-CGU); 2024 Mar; pp. 1–5. IEEE.

30. Jayaram M, Reddy SA, Praneetha B, Pujitha M, Chandra CS, Prakash KB. Smart cosmetics recommendation system based on skin condition using artificial intelligence. Skin. 2024;53(5).

31. https://www.kaggle.com/datasets/amaboh/skin-care-product-ingredients-inci-list