Revolutionizing the Fragrance Industry with Artificial Intelligence
A blog post by Kelsey Li
The “New Era” in the Fragrance Industry
The scent is considered to be one of the most mysterious senses and the fragrance industry has been dedicated to replicating the natural smell to serve the consumer’s olfactory appetite. However, the consumer group which led the main spending of this industry would want their fragrance to be unique, niche and even customized so that it could better complement various personalities. The new trend is calling for innovative ways to create new scents in this industry, and China as one of the largest consumer countries is, without doubt, the most potential market to explore such opportunities.
Our Innovation
In SAP S/4 HANA Consumer Industries Cloud, we have been collaboratively working with customers from the CP industry to help them solve their pain points. And the colleagues in Shanghai are also actively capturing local trends and opportunities to explore new innovations. With one of our new RISE with SAP customers in the Chinese market — Huabao, the flavor and fragrance company that ranked top in the local market, together we are leading this new trend of consumer personalized outcome with our technology capabilities.
Although Huabao is very experienced in the scent-making industry, the whole fragrance-making process and new flavor invention still heavily depend on the personal experience of perfumers, which takes as long as a dozen years to develop, and the formulation knowledge is saved nowhere other than with the perfumers. This slows them down from new innovations and understanding consumers need, not to mention predicting the trend.
To help the customer, our CIC Shanghai team brought in the breakthrough idea to digitalize scents, utilize Machine Learning and AI to build a consumer-focused flavor creation tool — Arobot.
Arobot is a tool which deploys machine learning to analyze and predict consumers’ preferences, trawl scent knowledge, generate formulas and recommend new fragrances catered specifically to different personalities. Behind the scenes, the model digitizes the scent notes, symbolic ingredients, and formula combinations. It also absorbs and learns from existing knowledge to create a formula library that will innovate, optimize, and enhance the formulas with minimal human expertise tweaks.
Arobot made its debut in November at the 4th China International Import Expo (CIIE) in Shanghai and showcased its astonishing capability. With a questionnaire to collect user’s preference of scents, Arobot creates the aroma profile user may like, generates the formulation accordingly, and completes the production automatically, all in 3 minutes to get the unique and catered fragrance ready.
The Value
The end solution we created via a POC helps Huabao to enable Direct to Consumer business model, produce personalized fragrance for consumers in segment of one, and integrate with digital manufacturing to automate the end-to-end C2M processes, so they can close the loop from obtaining consumer insights, to fragrance creation, production, and feedback collection for continuous improvement. It also turns the cumbersome fragrance making process which requires massive human expertise work and years of development into a semi-automated efficient one that only needs a few minutes with minor human interactions.
SAP is helping Huabao successfully transform from the traditional production process into a innovative, digitalized, intelligent and efficient way of developing new products. This solution presented the huge potential it could bring to the manufacturing business, it’s only a matter of time before AI technology becomes the norm in developing new flavors, personalized cosmetics and other consumers product.
