Creative Data > Creative Data
HUGE, New York / IL MAKIAGE / 2019
Overview
Credits
Why is this work relevant for Creative Data?
By using in store sales figures, return rates, quizzes results, in-store testing results, lab testing results and consumers interviews, we created an algorithm that let our ecom platform pick the perfect foundation for our customers, without ever seeing their face.
Background
Finding a decent foundation is the Holy Grail of beauty that many makeup-wearers can only dream of. Even if you find something that just kind-of-works for you, chances are you'll stick with it instead of risking spending more on something that won't. Finding the perfect shade implies trying hundreds of different products in store, and finding it online is downright impossible. Il Makiage sought to change that.
Describe the idea/data solution
We developed a shade-matching algorithm that can find anyone’s perfect tone without even seeing their faces. We combined hundreds of thousands of data points and information on more than 700 skin tones to create PowerMatch, a platform that uses machine learning to correctly predict a wearer's perfect shade of foundation, based only on their answers to a simple quiz. The algorithm has a 90 percent accuracy rate, and growing.
Describe the data driven strategy
For more than a year, IL MAKIAGE combined hundreds of thousands of data points and information on over 700 different skin tone combinations to create the PowerMatch Algorithm to help customers find their perfect shade of foundation online. The data science, R&D and engineering teams built a massive database of this information that uses machine learning to constantly evolve, resulting in more than a 90% accuracy rate of predicting the correct shade.
Describe the creative use of data, or how the data enhanced the creative output
On January 2019, we launch the algorithm on our ecom site, in the form of an easy and fun to follow quiz, to help women pick the perfect shade of foundation. In less than five minutes, women could answer questions about their skin tone, skin type, and even personal preferences, and based on that got a shade recommendation. To encourage users to try it, we offered customers the option to try the foundation at home for free for 14 days, alleviating any cost of risk for them. By using return rates, the algorithm keeps learning, now over thousands and thousands of purchases.
List the data driven results
Sales grew tenfold in the month of the launch. To date, more than one million consumers have taken the quiz. The launch of our algorithm was covered by top-tier national media across business, tech, consumer and trade outlets including O, The Oprah Magazine, Glossy, Engadget, Cheddar, HelloGiggles, CEW and New York Business Journal.
More Entries from Data-driven Targeting in Creative Data
24 items
More Entries from HUGE
24 items