Next Article in Journal
Physicochemical Properties and Composition of Peristomal Skin Care Products: A Narrative Review
Previous Article in Journal
Photoprotective Effect and Potential Mechanisms of Gardeniae Fructus Extract in UVB-Irradiated HaCaT Cells
Previous Article in Special Issue
Correction: Su, E.; Herman, S. Beyond Sulfate-Free Personal Cleansing Technology. Cosmetics 2025, 12, 14
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Conference Report

Artificial Intelligence Beauty Revolution—State of the Art and New Trends from the SCC78 Annual Meeting

1
R&D Head of Formulation, ChapStick, Suave Brands Co., Hackensack, NJ 07601, USA
2
Committee on Scientific Affairs (COSA), Society of Cosmetic Chemists (SCC), New York, NY 10005, USA
3
Bioactive Botanical Research Laboratory, Department of Biomedical and Pharmaceutical Sciences, College of Pharmacy, University of Rhode Island, Kingston, RI 02881, USA
4
Scientific Committee, New York Society of Cosmetic Chemists, Mount Freedom, NJ 07970, USA
5
Chinese American Cosmetic Professional Association, Princeton, NJ 08540, USA
*
Author to whom correspondence should be addressed.
Cosmetics 2025, 12(2), 73; https://doi.org/10.3390/cosmetics12020073
Submission received: 18 January 2025 / Revised: 19 March 2025 / Accepted: 3 April 2025 / Published: 9 April 2025

Abstract

:
The 78th Annual Society of Cosmetic Chemists (SCC) Scientific Meeting showcased the pivotal role of artificial intelligence (AI) in transforming the beauty and personal care industry. The session “AI Beauty Revolution” highlighted cutting-edge advancements, including AI-driven ingredient discovery, personalized product development, and sustainable practices. Key presentations explored applications such as computational tools for product benchmarking, precision prebiotics for microbiome modulation, and physics-based modeling combined with machine learning for antioxidant screening. The discussions emphasized the importance of combining AI insights with experimental validation to ensure accuracy and reliability while fostering innovation. As AI continues to drive personalization, efficiency, and sustainability in cosmetics, collaborative efforts across disciplines will remain crucial for realizing its full potential.

1. Introduction

The 78th Annual SCC Scientific Meeting & Showcase (SCC78), which took place from 11 to 13 December 2024, in Los Angeles, CA, USA, was a dynamic convergence of cutting-edge science, innovation, and industry expertise in the world of cosmetic and personal care sciences. Hosted by the Society of Cosmetic Chemists (SCC), this event brought together leading researchers, formulators, chemists, and industry professionals to explore the latest advancements and trends shaping the future of beauty and personal care. This year’s meeting featured engaging sessions, scientific presentations, interactive panel discussions, and award-winning keynote speakers on topics ranging from artificial intelligence (AI) in beauty and sustainable formulation to innovative skincare technologies and regulatory updates.
With the introduction and influence of AI exponentially growing in various related-world industries, the SCC Committee on Scientific Affairs (COSA), composed of national SCC board members and select industry and subject matter experts, developed the scientific program for the SCC78 annual meeting to include a session titled “AI Beauty Revolution”, which explored how cutting-edge AI is transforming the personal care industry. COSA envisioned the inclusion of an AI Beauty speaker session at SCC78 as an opportunity to provide attendees with both advanced AI learnings as well as a forum for active discussion and connection building between industry professionals who are unfamiliar with AI tools and its possibilities and those well-versed in the AI field. This session featured expert talks on AI-driven advancements in product benchmarking, precision prebiotics for personal care, and active ingredient discovery. Further, the session speakers provided attendees with learning opportunities on how AI is enhancing the formulation process, optimizing skincare solutions, and driving innovation in sustainable practices.
AI is revolutionizing the beauty and personal care industry by advancing personalization, innovation, and sustainability [1,2,3]. AI-driven tools enable personalized skincare solutions by analyzing individual skin profiles, preferences, and environmental factors to recommend tailored products. In ingredient discovery and formulation, machine learning accelerates the identification of novel compounds and predicts their efficacy, streamlining research and development [4]. Additionally, AI supports virtual try-on technologies using augmented reality, enhancing consumer experience by allowing real-time visualization of cosmetic applications [5]. AI also improves supply chain optimization and promotes transparent sourcing, contributing to more sustainable and ethical practices [6]. By analyzing consumer behavior and market trends, AI helps brands remain agile and responsive to evolving demands. Collectively, these advancements merge technology and science to drive innovative, consumer-centric, and environmentally responsible solutions, marking a transformative shift in the personal care industry. Dr. Angela Eppler, COSA, Committee Member (SCC) and R&D Head of Formulation (ChapStick, Suave Brands Co., Hackensack, NJ, USA), presided over this AI Beauty Revolution session, which included five presentations from the following expert speakers. Mr. Yahya Syed, co-founder and CEO of Potion AI (San Francisco, CA, USA), shared insights on leveraging AI to accelerate product benchmarking and ingredient discovery. His experience in navigating the complexities of skincare product development has driven Potion AI’s innovations in applying machine learning to streamline cosmetic formulation processes. Dr. Jaide Jensen, Head of Biotech at Arcaea (Boston, MA, USA), presented their work at the crossroads of synthetic biology and cosmetic science, highlighting approaches to microbiome modulation for enhanced personal care solutions. Dr. Haidong Liu, a materials scientist and computational modeler at Schrödinger Inc. (New York, NY, USA), discussed the application of computational chemistry and physics-based modeling to predict material behavior and improve the efficacy and sustainability of personal care products. Dr. Lun Yu, co-founder and CTO of MetaNovas Biotech (Mountain View, CA, USA), detailed advancements in the application of AI and deep learning for the discovery of bioactive ingredients. His work emphasizes the use of transfer learning to address data limitations in ingredient research. Dr. Hang Ma, a research assistant professor at the University of Rhode Island and principal investigator at the Bioactive Botanical Research Laboratory, described their efforts in integrating biological assays, proteomics, and machine learning to identify mechanisms of action for natural products in skin health applications (See the abstracts of presentations in the Supplementary Material).

2. Presentations

The Society of Cosmetic Chemists acknowledged Uncountable (San Francisco, CA, USA), the sponsor of the AI Beauty Revolution session, for which representative Joseph Sanz provided attendees with an introduction to the company’s cloud-based platform services which help the world accelerate the pace of innovation, from research to commercialization.

2.1. Applying AI to Product Benchmarking, Presented by Mr. Yahya Syed (Potion AI)

At SCC78, Yahya described how Potion is applying AI to drastically speed up product benchmarking—a process that typically takes hours—by representing tens of thousands of formulas as graph-based models and training graph neural networks to predict ingredient concentrations, chemical functions, and likely trade names for a provided benchmark ingredient list. Leveraging a database of more than 70,000 raw materials, the tool can identify viable ingredient candidates in seconds and present them for expert review, providing a powerful aid for R&D professionals, new formulators, and market researchers. In an effort to move the industry forward and iterate more quickly, an AI tool is developed to enhance its capabilities, with a particular focus on increasing data fidelity and expanding the number of benchmarking inputs.

2.2. Precision Prebiotics—Skin Microbiome Modulation for Cosmetic Benefits, by Jaide Jensen, Ph.D. (Arcaea, LLC)

At the SCC78 conference, Dr. Jensen presented an approach to developing microbiome-targeted ingredients for personal care utilizing automation for large data generation and machine learning. The research demonstrates a novel methodology for developing prebiotics that specifically modulates the skin microbiome. Two successful applications of the approach were showcased: a prebiotic-enriched deodorant that significantly reduced underarm odor by shifting microbial populations, and a prebiotic shampoo that achieved remarkable clinical results—86% improvement in scalp flakiness and complete elimination of redness among participants. These achievements represent a significant step toward more sustainable, biologically harmonious personal care solutions driven by machine learning and automation.

2.3. Screening Antioxidant Ingredients Using Machine Learning and Physics-Based Modeling, by Haidong Liu, Ph.D. (Schrödinger)

Antioxidants are important ingredients for cosmetic products to alleviate oxidative stress. However, high-throughput screening for new antioxidant candidates remains challenging experimentally. Data-driven machine learning models require a reliable dataset. At SCC78, Dr. Liu presented an efficient computational approach that combines physics-based and machine learning tools to address this issue. This approach only uses molecular structures as inputs. They used molecular quantum mechanical (QM) calculation and machine learning to predict antioxidant activity through the hydrogen atom transfer (HAT) mechanism. The team first constructed a library of flavonoid structures and then calculated the hydrogen dissociation energies of the hydroxyl group in solvents using QM. The machine learning model was trained and validated using the hydrogen dissociation energies from QM calculations. Their approach can easily screen thousands of molecules. This physics-based and machine learning combined approach can be used for other properties.

2.4. Transferring Knowledge from Synthetic to Natural Compounds: A Deep Learning Approach, by Lun Yu, Ph.D. (MetaNovas Biotech)

In this talk, Dr. Yu’s team tackles the challenge of learning from small datasets in predicting natural product bioactivity. By applying transfer learning, they leverage large datasets of synthetic compounds to enhance deep-learning model performance on natural compounds. Using FusionDTA, a state-of-the-art model, the team pre-trained on synthetic compound data and fine-tuned on natural compound data. The results showed significant improvements in prediction accuracy, with lower MSE and higher concordance index, particularly on novel scaffolds unseen during training. This highlights the power of transfer learning in overcoming data limitations, enabling more accurate predictions and accelerating ingredient discovery.

2.5. A Platform Integrating Biological Assays, Proteomic Analyses, Network Pharmacology, Machine Learning, and Target Binding Techniques for the Discovery of Skin Protective Natural Products, by Hang Ma, Ph.D. (University of Rhode Island)

Dr. Ma presented their work on how to leverage AI in the discovery and development of active cosmetic ingredients. Dr. Ma showed that a challenge in discovering natural products as active cosmeceutical ingredients is the lack of effective methods for extracting in-depth information from biological assays. By leveraging AI tools, researchers can efficiently obtain valuable insights, such as the mechanisms of action of active ingredients. Dr. Ma provided an example of using a proteomics-based approach to elucidate potential molecular targets involved in the anti-ferroptotic and skin-protective effects of a natural product (cannabidiol) in human skin keratinocytes [7]. Based on this method, Dr. Ma’s group further developed a system, namely, bioassays and AI network-based evaluations (BAINEs), which can be used for screening natural products to mediate skin conditions including oxidative stress, ferroptosis, skin inflammation, hyperpigmentation, and aging-related concerns. Central to the presentation is their development of the BAINEs system, which leverages AI-powered biomarker discovery and machine learning to analyze proteomics data, predict synergistic effects between ingredients, and identify novel mechanisms of action. Additionally, Dr. Ma showcases the use of surface plasmon resonance (SPR) to validate protein–protein interactions, such as the Nrf2-Keap1 pathway, enhancing the precision of ingredient efficacy studies. This innovative approach bridges biological research and practical skincare applications, demonstrating the transformative potential of AI in accelerating the discovery and validation of new active ingredients for skincare.

3. Speakers’ Perspectives on AI and Beauty

Mr. Yahya Syed views AI as a transformative technology poised to revolutionize the beauty industry through its ability to streamline key processes, including ingredient discovery, formulation optimization, and consumer trend forecasting. He anticipates that AI will significantly reduce the time, cost, and effort required to commercialize innovative ingredients and products, driving efficiency and fostering a new era of growth. By enabling greater accessibility and personalization, AI could democratize brand creation and expand consumer options, ultimately reshaping the industry’s landscape.
Dr. Jensen highlights the accelerating role of AI and automation in advancing the development of novel, high-performance cosmetic ingredients and products with unique functionalities. She emphasizes that as AI capabilities improve and datasets grow, the industry will be able to leverage these tools for enhanced precision and innovation. For professionals aspiring to enter AI-driven roles in cosmetics, she underscores the importance of mastering technical disciplines such as computer science, data science, computational biology, or chemistry. She also points out the critical need to understand the specific challenges of the beauty sector, which is best achieved through collaborative projects and direct industry engagement.
After seeing the great success of AI in drug development, Dr. Yu believes this success can be replicated in the beauty industry as well. At Metanovas, they harness AI to gain deeper insights into human biology and leverage these insights to design more effective and targeted bioactive ingredients. By applying advanced techniques like deep learning, knowledge graphs, and transfer learning, AI can identify novel compounds, predict their bioactivity, and optimize their performance for specific beauty applications such as skin aging, scalp health, and microbiome modulation. This AI-driven approach not only accelerates ingredient discovery but also enables the development of innovative, science-backed beauty solutions with proven clinical efficacy. Additionally, in response to the question “What would you suggest to a person at the entry level in the industry who wants to be more involved in AI-related work?”, Dr. Yu commented that “for those looking to get started in this exciting field, it begins with gaining sufficient domain knowledge in biology, chemistry, or cosmetic science to understand the challenges and opportunities. Next, getting hands-on exposure to AI projects—whether through online courses, collaborative research, or open datasets—will help you build technical expertise. Most importantly, understanding how to formulate a problem within the AI framework is key: identify the question, collect relevant data, and determine the appropriate models and methods to solve it. By bridging domain expertise with AI skills, beginners can actively contribute to advancing AI for beauty innovations”.
On the Role of AI in Cosmetics and Personal Care, Dr. Liu thinks that the rapid rise of AI has led to a lot of excitement about its potential to revolutionize the cosmetics and personal care industry. However, it is important to remember that AI is just one tool in a holistic computational chemistry toolbox. Like other computational chemistry approaches, AI has its own strengths and shortcomings. One of the main challenges with AI is that it requires a lot of high-quality data to train the models. In the cosmetics and personal care industry, these data are often scarce. As a result, AI models can sometimes be inaccurate or unreliable. In contrast, physics-based simulation can generate data based on realistic computational models of novel ingredients, cosmetics formulations, and packaging materials. The data generated are interpretable, allowing researchers and engineers to make informed decisions before embarking on costly experimental testing. On the Future of AI in Cosmetics and Personal Care, Dr Liu thinks that, despite the challenges, AI is still a promising technology for the cosmetics and personal care industry. As the amount of available data increases, AI models will become more accurate and reliable. This will allow AI to play a more significant role in product development, formulation optimization, and quality control. However, it is important to remember that AI is not a silver bullet. It is just one tool in a holistic computational chemistry toolbox. By combining AI with other computational chemistry and experimental approaches, you can achieve the best possible results for your product development efforts.
Dr. Ma believes that AI has become a mainstream approach for research and development in the cosmetic and personal care industry, revolutionizing how products are discovered and formulated. By providing deeper insights and data-driven analyses, AI helps researchers, chemists, biologists, formulators, and decision-makers gain a more comprehensive understanding of active ingredients and formulations, ultimately enabling better-informed decisions. Among the various AI applications, multi-omics approaches like proteomics and genomics are particularly valuable, offering essential tools for discovering new ingredients and elucidating their mechanisms of action. Given the interdisciplinary nature of AI, collaborative efforts are more critical than ever, requiring teamwork across multiple fields to maximize AI’s potential. However, while AI is transformative, it should be used with caution and always complemented by experimental data to ensure accuracy and reliability. Balancing AI with empirical validation safeguards the integrity of scientific findings and enhances innovation in the beauty industry.

4. Conclusions

The Society of Cosmetic Chemists (SCC) 78th Annual Meeting highlighted the transformative role of AI in the beauty and personal care industry, showcasing innovations across ingredient discovery, product formulation, consumer personalization, and sustainability. The session AI Beauty Revolution emphasized the interdisciplinary nature of advancements, blending computational biology, machine learning, proteomics, and synthetic biology to address pressing industry challenges. Presentations covered diverse applications, from AI-driven ingredient benchmarking to leveraging machine learning for microbiome modulation and antioxidant screening. The integration of AI with traditional scientific methodologies, such as physics-based modeling and proteomics, illustrated the complementary nature of these approaches in fostering innovation. The discussions underscored the importance of balancing AI insights with experimental validation to ensure scientific accuracy and reliability. Speakers collectively envisioned a future where AI drives unprecedented personalization and efficiency in product development while supporting sustainable and ethical practices.

Supplementary Materials

The following supporting information can be downloaded at: https://www.mdpi.com/article/10.3390/cosmetics12020073/s1, Abstracts of all presentations presented in the Session AI Beauty Revolution at the SCC78 Meeting.

Author Contributions

Conceptualization, writing—review and editing, A.R.E. and H.M. All authors have read and agreed to the published version of the manuscript.

Funding

This research received no external funding.

Acknowledgments

This symposium was organized by the SCC Committee on Scientific Affairs (COSA) and sponsored by Uncountable (San Francisco, CA, USA).

Conflicts of Interest

H.M. received the SCC 2024 Hans Schaeffer Award and is an equity holder of Ocean State Bioactives. A.E. is employed by Suave Brands Co. and was a member of the SCC committee responsible for organizing the scientific program, including the AI Beauty Revolution session, for the 78th Annual SCC Scientific Symposium; the referenced research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

References

  1. Georgievskaya, A.; Tlyachev, T.; Danko, D.; Chekanov, K.; Corstjens, H. How Artificial Intelligence Adopts Human Biases: The Case of Cosmetic Skincare Industry. In AI and Ethics; Springer: Berlin/Heidelberg, Germany, 2023; Volume 5, pp. 105–115. [Google Scholar] [CrossRef]
  2. Grech, V.S.; Kefala, V.; Rallis, E. Cosmetology in the Era of Artificial Intelligence. Cosmetics 2024, 11, 135. [Google Scholar] [CrossRef]
  3. Elder, A.; Ring, C.; Heitmiller, K.; Gabriel, Z.; Saedi, N. The Role of Artificial Intelligence in Cosmetic Dermatology—Current, Upcoming, and Future Trends. J. Cosmet. Dermatol. 2021, 20, 48–52. [Google Scholar] [CrossRef] [PubMed]
  4. 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, 2066–2077. [Google Scholar] [CrossRef] [PubMed]
  5. Mihăilă, R. 3D Virtual Garment Simulation and Facial Expression Recognition Technologies, Beauty Filter-Based Appealing Self-Presentation and Generative Artificial Intelligence Virtual Try-on Tools, and Deep Learning-Based Gesture Recognition and Augmented. J. Res. Gend. Stud. 2023, 13, 54–68. [Google Scholar]
  6. Sanghavi, K.; Mehta, H.; Pawade, G.; Konde, M.; Singh, S.; Seetha, R. Applications of Machine Learning in Detecting Unethical Sources of Raw Materials in Supply Chains in the Cosmetic Industry. In Proceedings of the 2024 4th International Conference on Sustainable Expert Systems (ICSES), Lekhnath, Nepal, 15–17 October 2024; pp. 716–720. [Google Scholar] [CrossRef]
  7. Li, H.; Puopolo, T.; Seeram, N.P.; Liu, C.; Ma, H. Anti-Ferroptotic Effect of Cannabidiol in Human Skin Keratinocytes Characterized by Data-Independent Acquisition-Based Proteomics. J. Nat. Prod. 2024, 87, 1493–1499. [Google Scholar] [CrossRef] [PubMed]
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

Share and Cite

MDPI and ACS Style

Eppler, A.R.; Ma, H. Artificial Intelligence Beauty Revolution—State of the Art and New Trends from the SCC78 Annual Meeting. Cosmetics 2025, 12, 73. https://doi.org/10.3390/cosmetics12020073

AMA Style

Eppler AR, Ma H. Artificial Intelligence Beauty Revolution—State of the Art and New Trends from the SCC78 Annual Meeting. Cosmetics. 2025; 12(2):73. https://doi.org/10.3390/cosmetics12020073

Chicago/Turabian Style

Eppler, Angela R., and Hang Ma. 2025. "Artificial Intelligence Beauty Revolution—State of the Art and New Trends from the SCC78 Annual Meeting" Cosmetics 12, no. 2: 73. https://doi.org/10.3390/cosmetics12020073

APA Style

Eppler, A. R., & Ma, H. (2025). Artificial Intelligence Beauty Revolution—State of the Art and New Trends from the SCC78 Annual Meeting. Cosmetics, 12(2), 73. https://doi.org/10.3390/cosmetics12020073

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop