“Fragrance is really a bit of a black box,” Johan Chaille de Nere, director of digital transformation at Givaudan, told Business Insider (BI). Julia Dufosse for BI
Perfume manufacturers use complicated algorithms to create unique scents for perfume lovers.
Givaudan launched its AI tool Myrissi last year to demystify fragrance development. NOS Emotiontech is another company that uses personalized consumer data to support perfumers.
Chaille de Nere, director of digital transformation at Givaudan, said AI could support sustainability measures.
This is a machine translation of an article from our US colleagues at Business Insider. It was automatically translated and checked by a real editor.
The sense of smell is perhaps the most powerful human sense. Think of the scent of fresh lavender or an evergreen forest; they can bring you peace or remind you of something unpleasant. You have no control over how they affect you.
The connection between smell and feelings has fascinated scientists for decades. Every person perceives scents and feelings differently, which raises the question of why we react to scents in a certain way.
In her book The Scent of Desire, neuroscientist Rachel Herz theorizes that smell was the first sense to develop in the brains of living beings to protect them from danger. This cognitive development is now known as the amygdala, a part of the brain that interacts with our olfactory receptors to detect danger and generate fear.
In one Study, conducted by Herz and a group of collaborators at Brown University, the team found that scents can trigger memories and influence mood. These memories are created when the olfactory cortex processes a smell and communicates with the limbic system, which influences behavior and emotions and causes us to react in a certain way.
Perfume manufacturers take advantage of this science. Some are taking a technology-based approach, using artificial intelligence to create suggestive, customized scents for consumers.
“Creation is such a beautiful thing,” Frederik Duerinck, co-founder of tech fragrance company EveryHuman, told Business Insider (BI). “It’s such a fulfilling experience.”
But it is not easy. To create custom scents, companies need to know how customers respond to different aromas—and that’s hard to gauge when people can’t communicate abstract feelings.
“We have the same difficulty deconstructing our emotional experiences with words as we do articulating our olfactory experiences,” Hertz says in “The Scent of Desire.”
Read too
The million-dollar business with a beautiful smile: How good are the promises of “Dr Smile” really?
AI to decode scents
Givaudan, one of the world‘s largest manufacturers of custom fragrances and flavors for the beauty and food industries, has focused on using AI to decipher the complexities of smells for over a decade. The company works on the business-to-business side of the industry, designing and creating fragrances for various companies worldwide.
“Scents are really a bit of a black box,” said Johan Chaille de Nere, director of digital transformation at Givaudan. “And AI helps us better understand and decipher what the consumer is really feeling.”
Givaudan launched its AI tool Myrissi last year to demystify fragrance development. With a database of more than 25,000 consumer responses from surveys and product testing, the company’s technology makes associations between scents and colors to create customized mood boards for brands developing scents.
NOS Emotiontech, formerly No Ordinary Scent, is another company that uses personalized consumer data to support perfumers. Initially, the Swedish company offered perfumes for direct sales through an AI platform that analyzed three photos submitted by users.
Now the company is focusing on its business customers, using an AI algorithm and existing customer data to create briefs that help brands create multi-sensory experiences.
Using scientific data and its trained algorithm, the company can also figure out which “scent families and notes” can “evoke specific emotional responses,” NOS Emotiontech founder Sandra Kinnmark told BI.
For example, a video game company commissioned NOS Emotiontech to fill its gaming studio with a personalized scent that would help participants feel at home and forget about time while playing. The scent focused on citrus and solar notes to increase feelings of happiness.
A woman tries out scents in one of NOS Emotiontech’s private perfume workshops. Angelica Lonnberg
Read too
Two cosmetics founders want to get started in Germany with fresh millions – this is their pitch deck
The Swedish company has also teamed up with the Hallwyl Museum, one of Stockholm’s oldest museums, to develop a guided “fragrant tour” where visitors can “actually experience stories from that time,” says Kinnmark.
NOS Emotiontech designed five bespoke scents that were distributed on strips in different areas of the museum. The scent in the dining room, for example, contained primarily floral and citrus aromas to emphasize the smell of flowers and exotic fruits that were popular at the time. The scent in the Armory Hall emphasized wood and cardamom to underline the tour guide’s discussion of colonial trade.
A new kind of signature scent
Some perfume brands use technology to decipher scent preferences and create personalized scents.
EveryHuman uses its Algorithmic Perfumery AI platform to create three customized perfumes for each customer. This involves collecting data from a survey in which customers are asked over 20 personal questions, including “What are your favorite things to do?” and “What color looks best on you?”
“It’s really a way for people to engage with smell on a much broader level and recognize their own identity,” said Frederik Duerinck, co-founder of EveryHuman.
The three scents are created based on interpretations of the data, he said. A perfume is created from the answers to the survey’s psychological questions. The second combines the psychological responses with the user’s demographic information, such as age and location. The third perfume takes into account how customers interacted with the survey, for example how much time they spent on a question.
Frederik Duerinck describes the Algorithmic Perfumery machine as a “small factory”. HILLSIDE
Read too
Researchers are developing AI that is supposed to improve the taste of beer – the first results are surprising
Each resulting perfume consists of 46 “building blocks”, as EveryHuman calls its specific fragrance blends, with each building block containing between two and 20 ingredients. Some building blocks are more familiar scent profiles like “rose” and “grapefruit,” while others are more abstract like “pure” and “metallic.”
According to Duerinck, the tool can create over 500 billion scent combinations.
“This platform is about unlocking the medium of scent so people can access it more easily,” said Anahita Mekanik, co-founder of EveryHuman.
In November, EveryHuman partnered with the Flagship store from The Fragrance Shop in London so that customers could try out the perfume machine.
A perfume reviewer who goes by TJ Talks Scents told BI that he tried the AI tool and that it felt less daunting than the trial-and-error method of buying perfumes online. “I think it’s a good idea because some people don’t know what they like in a perfume,” he added.
He said the machine had some technical difficulties, but he liked two of the three scents it generated because they matched his preference for sweet and woody notes. He added that the scents made him feel warm, even though he lives in the UK, where the weather is often cold and wet.
AI could prevail in the beauty industry
One of the biggest fears surrounding AI is that it could put people’s jobs at risk.
Chaille de Nere, director of digital transformation at Givaudan, told BI he doesn’t want this to happen in the perfume industry. He said he believes that “AI can support and inspire our perfumers, but it cannot replace them.” NOS Emotiontech takes a similar stance. While the briefs the company shares with brands are generated by AI, the company employs perfumers to create the scents.
The Algorithmic Perfumery machine creates three perfumes in front of customers. HILLSIDE
Read too
Secret project “Theia” revealed: Amazon is developing an AI tool that will redefine our online shopping experience
But some experts worry whether the AI initiatives will last. Chaille de Nere called personalized perfumes a “consumer trend” resulting from the industry’s experimentation with the new technology. Kinnmark added that she is concerned that personalization “leads to less” because it adds more products to the beauty industry and counters current trends to limit spending on a variety of products.
AI could have a lasting impact on the industry’s environmental regulations. Chaille de Nere said AI could support sustainability measures by creating chemical compositions that are produced ethically and with safe materials. He added that Givaudan is using AI to replace ingredients that have been banned by local authorities or regulators due to their negative carbon footprint. In 2022, the chemical compound Lilial, commonly found in floral perfumes, was banned in all European Union products due to allergenicity concerns.
While the role of AI in the beauty industry is yet to take shape, the perfume industry is betting on this technology. Perfume is moving further away from its status as a luxury item, and AI could be the key to making more scented fragrances for more people.
For Chaille de Nere, this could also mean rethinking the role of perfume as a beauty product. “The main power of a fragrance is not that you like it or dislike it,” he said. “The main power is to arouse emotions”.
Read the original article Business Insider.
Read too
Up to 1.2 million euros: These are the most expensive perfumes in the world