Retail

Proven Skincare Taps AI To Personalize Beauty

Proven Skincare Taps AI To Personalize Beauty

The claims that skincare and beauty brands make about their effectiveness never fail to be lofty – usually offering some combination of promises that using a specific product will make one’s skin appear to be softer, healthier, more youthful and more “glowy” within a few days or weeks. But, as many shoppers have gone on to find out, making a lofty claim and actually delivering on it are two very different things.

This was the experience that prompted Proven Skincare Founders Ming Zhao and Amy Yuan to found their own line of products. Yuan noted she had suffered from skin issues for her whole life, partially caused by allergies. Zhao, on the other hand, noted that a very stressful job in private equity had “done a number” on her skin – and that no matter how many miracle creams or products she tried, nothing was really working right.

“I was very frustrated, and I felt betrayed by our beauty industry,” Zhao said. “And eventually, what actually worked for me were customized products made by a few different facialists.”

The spark that hit her, Zhao said, was that a really innovative beauty brand would find a way to tailor their products to the specific skin needs of the consumer. But how to do it? That was where Yuan came in, with her background in computation physicals.

“I’ve done a lot of big-scale, supercomputing simulations,” she told us. “So I wondered if I could create an AI engine that gathers reviews for me to find skincare products that are automatically matched to my skin.”

When she presented her data-based approach to matching people to the right skincare routines via the magic of AI, the idea for Proven Skincare was ignited.

And the data crawling kicked off.

The core idea is to take the research project element out of choosing a skincare product. And that research is extensive, according to Zhao – the average person spends 45 minutes to 1.5 hours researching before they buy any beauty products. But it isn’t very effective, as 55 percent of women report that they remain unsatisfied after making a purchase.

“And that’s because of the proliferation of information that’s out there. No single person is capable of reading that amount of information in order to make a sound decision,” Zhao said.

Their AI product, then, becomes the set of eyes that can review and distill all usable data from millions of online testimonials for skincare products, plus a much smaller subset of publicly available, peer-reviewed, scientific research papers. The overall goal is to take that collated mountain of data and turn it toward programming customized skincare products that work.

“We built machine learning and artificial intelligence algorithms on top of that data to understand the correlations and interconnections between people’s skin and the ingredients that work for each person,” Zhou said.

When customers first log onto the site, they fill out an online questionnaire about their skin concerns, lifestyle and environment – most of the standard questions one is asked during a dermatologist visit. The questionnaire also asks about visible genetic background, such as ethnicity and skin tone, to help determine which ingredients to use. Then, the survey is matched against Proven Skincare’s AI, and a customized set of in-house formulations is sent to the consumer’s door.

Will Proven prove itself? As is always the case with very young startups, it can be hard to make a prediction – and Proven is still very young, as it just launched in November. The buzz has been big and early reviews have been good – but if retail has taught any lessons in the last few years, it is that there are no sure bets or certain outcomes. And, of course, AI-generated beauty routines is a concept that Proven will have to, well, prove out to its potential customers.

The technology the company uses certainly comes with a solid pedigree: The AI they created, the Skin Genome Project – which aggregates data from eight million consumer reviews, 100,000 skincare products, 20,000 ingredients and 4,000 academic journals – won a 2018 MIT AI Idol award.

And more importantly, Zhao noted, people want skincare products that work. In fact, she herself wanted them so badly a few years back that she was willing to pay a skin guru “a small fortune” to help her find the right routine. Proven aims to use AI to generate the same outcome that guru did – without charging the small fortune.

“[Proven is] based on the belief that personalized products made with you in mind have a much higher efficacy level, especially when we combine the knowledge that’s already out there,” Zhao noted.

——————————–

Latest Insights:

Our data and analytics team has developed a number of creative methodologies and frameworks that measure and benchmark the innovation that’s reshaping the payments and commerce ecosystem. The PYMNTS Next-Gen AP Automation Tracker, is a monthly report that highlights the most recent accounts payable developments and automated solutions that are disrupting how businesses process invoices, track spending and earn rebates on transactions.

TRENDING RIGHT NOW

To Top