We use cookies essential for this site to function well. Please click “Accept” to help us improve its usefulness with additional cookies. Learn about our use of cookies, and collaboration with select social media and trusted analytics partners here

Maximizing energy output using renewables equipment
Optimizing vessels' engines for greener maritime
Enabling remote diagnostics using data from wearables
Life Sciences
Utilizing AI across the medical treatment value chain

Kozhya: Reinventing skincare with AI

Speak with an AI/ML expert in your industry
Contact us
View our cases to discover what we have reaserched

About customer

Our client, an innovative skincare startup, aims to disrupt this industry with AI-assisted medicinal skin care development and recommender system alongside an alternative serum delivery device.


Individual skin treatment plan development requires multiple visits to the dermatologist. It is expensive for a patient from a financial and timing point of view.

The R&D process that delivers medicinal skincare is associated with expensive failures. Usually, it requires a significant lab and human resources to create a new serum. Multiple candidates are weeded out in the process due to instability, insolubility, or incompatibility of components.


To ensure remote assessment of a patient’s skin condition, we use algorithms powered by artificial intelligence from a patient’s face image. This automated test is later automatically combined and aligned with the questionnaire results. As a result, a personal skincare program is created interactively, without a need to visit a dermatologist.

Innovative serums are composed of qualitatively and quantitatively by machine learning technology. Thus, the choice of perspective components is narrowed and incompatible combinations are excluded prior to experimental phase.



  • Standard time consuming and costly personal skin care plan creation
  • Serum development process with high degree of risk


  • Fast, interactive and fully digital personal skin care plan development done at home
  • Serum composition is predicted via machine learning, reducing the risks of laboratory failures by 63%