Authors: Alexander Goslin, Hazel Ticas, Morgan Covarrubias
Mentors: Daniel Scott
Insitution: Utah Valley University
In the evolving realm of personal care product development, striking a balance between ingredient choice, manufacturing intricacies, and consumer demands is pivotal. As the industry grapples with escalating costs and the clamor for novelty, there's an imperative to find methods that refine the development pathway, keeping both product quality and cost-effectiveness in check. Machine Learning (ML) emerges as a promising contender, proposing a data-centric route to formulation - from discerning patterns to forecasting efficacies, and even creating formulas themselves. This study delves into the intricacies of leveraging ML for personal care formulations, specifically emphasizing its role in substituting ingredients to either amplify a product's qualitative facet or reduce production costs. Despite the allure of ML, its integration into personal care isn't without challenges, given the industry's unique regulatory, consumer-centric, and trend-driven landscape. Through rigorous testing, evidence-based enhancements, and in-depth analysis, we aim to shed light on ML's functional dynamics in cosmetic formulations, underscoring both its potential dividends in cost and quality.