Symrise, one of the world’s leading manufacturers of fragrances and flavorings, is charting creative paths. In partnership with IBM Research, the company is currently developing a method of using artificial intelligence (AI) to create perfumes based on digital fragrance models. Philyra, as the project is called, uses AI developed by IBM Research for product design technology. Its first project involves the creation of two fragrances for the customer O Boticario. Both fragrances will be brought to market in 2019.
“The art and science of designing a winning perfume has been something we at Symrise have been doing for more than 200 years. Now our perfumers can work with an AI apprentice by their side, that can analyze thousands of formulas and historical data to identify patterns and predict novel combinations, helping to make them more productive, and accelerate the design process by guiding them toward formulas that have never been seen before,” stated Achim Daub, President of Symrise Scent & Care.
Compared with other computer-aided models from IBM Research for other industry branches, creating fragrances requires highly detailed precision. Even if the system deviates only minimally from the specified amounts, it either makes or breaks a new perfume. Philyra uses a data-driven approach and accesses a gigantic data bank consisting of fragrance formulas, data about fragrance families – fruity, oriental or flowery – as well as historical data. The system uses artificial intelligence and a treasure trove of data to create, for example, a fragrance especially for Brazilian male millennials.
In the fragrance business in particular, the market demands new creations every season. AI identifies existing fragrances and suggests complementary additional components and formulas. Symrise perfumer David Apel from the New York Studio took these suggestions and then tweaked them minimally, to emphasize a certain fragrance note, and improve how long it lasts on the skin. This collaborative work has resulted in two fine fragrances that Symrise will present next year.
This article aims to alert the medical community and public health authorities to accumulating evidence…
This article is about the neural conundrum behind the slowness of human behavior. The information…
We live in a world where we slather ourselves in more anti-aging creams than a…