Measuring makeup spreadability with rheology and machine learning
Measuring makeup spreadability with rheology and machine learning lead image
Quantifying the sensory texture of makeup is important for the cosmetics industry. Lee et al. used rheological properties based on large amplitude oscillatory shear (LAOS) measurements to model cosmetic formulation spreadability.
LAOS tests impose shearing strain in the form of high-amplitude sine waves. The resultant stress response provides useful information about cosmetic rheological properties.
“As a rheologist, I am always fascinated by material deformation and flow. I was applying lotion on my face one day when I realized there is a parallel between the cosmetics application procedure and LAOS, in that both involve recurrent, big deformations,” said author Jun Dong Park. “The thought occurred to me that analyzing the rheological behavior of cosmetics under LAOS may be strongly connected to the sensory texture felt by consumers.”
The model takes in rheological data, then predicts makeup spreadability using a random forest regression algorithm. The team examined two different inputs, one typically used in the cosmetics industry and LAOS measurements. The latter were more effective as inputs, improving the model’s performance.
“This enhancement is attributed to the sequence of physical process analysis, which separates information on the elastic and viscous transition from the stress response under LAOS,” said Park. “Despite the relatively limited amount of data, our prediction model performs well, which is attributed to these new metrics that effectively represent the actual rubbing of cosmetics.”
In the future, the model could reduce the time and money spent on sensory texture testing. The authors plan to extend it to examine different cosmetic textures such as stickiness and adhesiveness.
Source: “Predictive model for the spreadability of cosmetic formulations based on large amplitude oscillatory shear (LAOS) and machine learning,” by Suhyun Lee, Sung Ryul Kim, Hyo-Jeong Lee, Byoung Soo Kim, Heemuk Oh, Jun Bae Lee, Kyunghye Park, Yoon Ju Yi, Chun Ho Park, and Jun Dong Park, Physics of Fluids (2022). The article can be accessed at https://doi.org/10.1063/5.0117989 .
