Discovering a New Beverage Flavor for Millennial Females in Japan

A major Asian fruit beverage company located in Japan has been experiencing a continuous decline in sales over the past year. They reached out to us for a solution.

An exciting and familiar problem came to us last year. It's a problematic issue for many food and beverage companies as they develop new products that delight their customers. The following is the story of just one such company.

A major Asian fruit beverage company located in Japan has been experiencing a continuous decline in sales over the past year. Everyone believed that new products needed to become available on the market to mitigate the sales decline. Senior managers felt a deeper understanding of consumer sensory perception and preference was called for to develop new market-winning products.

The company used traditional sensory panels for its new product development (NPD) cycle. Each NPD iteration takes about five months to complete, is extremely costly, and does not carry a guarantee of success. Time was of the essence if they were to correct the downward spiral. They reached out to us Gastrograph AI for a solution. 

Read The Full Case Study: How a Drink Manufacturer Uncovered a New Beverage Flavor for Millennial Females in Japan

The Goal

Our objective, given the parameters of the problem, was to understand the perception and preferences of the target market, test and validate client-generated flavors (grapefruit, strawberry, and grape) in the target market, and identify new flavors with market potential. We deployed Gastrograph AI, a new artificial intelligence technology used to understand better consumer sensory perception and preference of food and beverage products in a market context. We use this technology to help clients develop new competitive products and optimize existing brands.  

The Approach

Gastrograph AI took a 2-pronged approach to tackle the problem. 

Our first step was to develop a benchmark for market performance based on flavor and texture profiles for millennial females in Japan.

In addition, it shows non-competitive products and areas of low competition across flavors, preferences, and demographics. Second, we began our Computational Creativity platform, which explores new combinations of flavors that do not currently exist on the market. It also predicts the preference distribution of a target population for products without actual product formulation or sampling.

Initial Analysis: Current product benchmark

The Client provided a current lemon flavor beverage product for analysis. The following graphs demonstrate the objective flavor profile (OFP) and the predicted preference distribution of the product in the target market.

original flavor profile

Preference shows a bi-modal distribution, with an average Perceived Quality (PQ) score of 4.2. 

  • The distribution predicts about 17% of consumers will dislike this product and give the product a PQ score of 3
  • 25% of the consumers are going to like this product and give it a PQ score of 5
  • 7% of the consumers will love this product; they will give the product a 7 out of 7.


Current Preference Distribution


demographic archetype pine drink

The graph above shows the preference distribution of population in the target market across age and sex. We can see the product performs well among 20-year-old women in the target population. 

From the Initial Analysis of the benchmark product, we realized two significant factors:

  • The overall performance of the current product is somewhat competitive.
  • The client will only accept new products that perform at least as well as the current benchmark.


Let the AI Create: Proposed flavors fall flat

With Gastograph AI, you can test any product modification by testing different versions of the same product and predicting the reaction of a consumer group. Unfortunately, none of the flavors (grapefruit, strawberry, and grape) suggested by the Client surpassed the performance of the original product. The timing was now urgent for the client team to develop new answers. At this point, we introduced Computational Creativity, a Deep Market Insights service.

Computational Creativity:  Validating True AI In Action

We needed to set some essential boundaries for AI to generate new results. In this case, it's for millennial females in Japan. We tuned the AI to be exploratory to test new flavors, including those that are generally uncommon to the target market. 

The output of the AI? Pine

OFP + Pine

ResultA New Flavor for New Market Share

The preferred beverage flavor for millennial females in Japan is pine.

Gastrograph AI predicts that over 40% of the target demographic will give this new pine flavored beverage a PQ of 6 or higher. Although the Client's marketing team did not suggest pine as a unique flavor, it does not mean that the pine flavor isn't preferred. Gastrograph AI can sense potential pent-up demand in the target market.

Next Steps

The Gastrograph AI team will work closely with the Client's R&D team to hit the target flavor profile and develop the new product.  

To read the full case study on how we used our AI to discover a new beverage flavor for millennial females in Japan, click here.

Get In Touch

Want to learn how Gastrograph AI can work with you to develop and optimize new and existing products? 

Request a Demo

Similar posts

Stay up to date with Gastrograph AI

Be the first to know about company updates and industry-related news, straight from our internal subject matter experts.