Close Ad

The Spoon

Daily news and analysis about the food tech revolution

flavor

With Series of Partnerships, Givaudan Positions Itself for an Alt Protein Future

Swiss flavor manufacturer Givaudan recently announced plans to open a new Cultured Food Innovation Hub by 2022. This is the latest in a flurry of new initiatives that suggest the company is positioning itself as a major player in the alternative protein industry.

Givaudan and its partners hope to support cell-cultured protein startups as they perform research and development and bring new products to market. At the Innovation Hub, startups will have access to cell-culture and bio-fermentation equipment, as well as a product development laboratory.

With many countries awaiting regulatory decisions for cell-cultured products, Givaudan appears to be anticipating a growing demand for business-to-business services in the industry. The company already partners with plant-based meat and dairy startups to develop, prototype, and test products. This foray into cultivated protein territory means they’ll stay on the cutting edge as cell-culture products make their debuts.

The facility will be built outside of Zurich, and will be owned in partnership with plant equipment manufacturer Bühler and retail food giant Migros—a partnership that’s interesting in its own right. Pooling their ranges of expertise, the companies should be able to offer comprehensive, turnkey services to would-be cell-cultured meat manufacturers. Fabio Campanile, Givaudan’s Global Head of Science and Technology, Taste & Wellbeing, commented on the partnership in a recent press release:

“Bühler contributes with industry-leading solutions that are used in the scale-up and production of thousands of food products around the world; Givaudan brings in centuries of experience and knowledge in every aspect of taste, including all kinds of meat alternatives, and deep expertise in biotechnology, to product development; Migros is known for its competence in customer interaction and market cultivation.”

Givaudan has also been keeping busy with its own research and development efforts, working on producing sustainable flavor ingredients for alternative meats and other products. Last month, The Spoon reported on Givaudan and Ginkgo Bioworks’ joint effort to develop new flavor and fragrance ingredients through bio-fermentation. More recently, the company announced another partnership with Danish biotech company Biosyntia—this one focused on transforming natural sugars into flavoring agents.

We may see more companies from outside of the alternative protein industry take an interest in cell-cultured meat. German life sciences and electronics manufacturer Merck KGaA is now offering technology solutions (from process design to growth medium formulation) for cell-cultured manufacturers. These big-name partners should help smaller startups to bring their products to market more quickly.

Spoonshot Launches Free Version of its AI-Based Flavor Pairing Tool

Spoonshot, which uses artificial intelligence (AI) to uncover novel flavor combinations, has launched a free version of its tool that is accessible to anyone. Spoonshot CEO and Co-Founder, Kishan Vasani spoke about the new level of service at The Spoon’s Food Tech Live event earlier this week.

Up to this point, Spoonshot’s platform has been a B2B play, meant for CPG companies and foodservice operators looking ahead to see what the next food and flavor trends might be. As we wrote last year when Spoonshot raised $11 million:

To get ahead of the curve, Spoonshot’s platform examines data from across a vast number of food-related sources including online menus, food science, CPG ingredients and online food communities. Spoonshot runs this data through its proprietary machine learning and AI algorithms to help companies identify existing and novel flavor combinations.

The key word here is “novel.” When you enter a flavor like “banana” into Spoonshot’s Ingredient Network tool, the service brings back a number of potential flavor combinations and scores them based on novelty. Combining banana + chocolate is common, but combining banana + aloveera juice is something that probably hasn’t occurred to most people and a combo that Spoonshot says will be tasty.

Armed with this novel combination, a restaurant or CPG company could go about building a new product that will appeal to consumers.

Launched at the start of the new year, Spoonshot’s new free tier of service now allows anyone to try its AI platform out (pricing starts at $99/month). Chances are good that most of us in our everyday lives don’t need enterprise-grade artificial intelligence to uncover novel flavor combinations. But aside from being a fun (and free) little distraction for everyday chefs, it could also be useful for small CPG or restaurant owners that don’t have R&D budgets to expand their offerings.

SKS 2019: IBM and McCormick Use AI to Make the Best Possible Barbecue Chips (and More)

Say you’re developing a new barbecue potato chip. You’re using spices from McCormick, which has not one, not two, but over 100 types of garlic flavoring. How do you decide which garlic(s) to use, and in which combinations, to make the best product for your target demographic?

That’s where artificial intelligence (AI) can help. Last year, McCormick, the largest flavor company in the world, went public with its five-plus-year partnership with IBM to build a flavor platform using machine learning. We dove deep into this partnership at SKS 2019, when The Spoon’s Chris Albrecht spoke with McCormick’s Chief Science Officer Hamed Faridi and IBM Principal Researcher Richard Goodwin about how AI can help make better, tastier products in less time and with fewer dead ends.

Check out the video below to watch the entire panel (it’s super nerdy and cool).

Hamed Faridi on the SKS 2019 stage. (Photo: The Spoon)

To whet your appetite, here’s a quick overview of what Faridi and Goodwin discussed in the session.

“The [CPG] iterating process is a very time-consuming, old system,” said Faridi during his onstage presentation. “But that’s the only thing the industry has.” All of that changed when Faridi was driving home and heard an NPR interview with a scientist from IBM’s Chef Watson, a program that develops bepsoke recipes based off of chemical flavor affinities (for example, leeks and chocolate.) Immediately, he was struck: this was the missing piece of the puzzle to develop better products in a smarter way.

Computers can’t taste or smell, so how do they know which flavors taste well together? That’s where data comes in. McCormick has kept all of its data from various flavor development processes and product experiments since the 1980s. IBM’s machine learning algorithms can take those data points and make suggestions about new ingredient combinations without having to go through all the trial, error, and staff training that a human R&D team requires.

The result is a 70 percent reduction in product development time and increased stickiness in the market. Faridi said that the IBM partnership is working so well they expect all of their labs will be using AI by late 2021.

This session was a fascinating look into how a flavor giant and a technology giant have teamed up to make better everyday products. Watch the full video below and get ready for more SKS 2019 content coming your way over the next few weeks!

SKS 2019: Case Study: McCormick & IBM Build an AI-Powered Flavor Platform

Ai Palette Raises $1.1M in Seed Funding for its Food Trend Prediction Platform

Ai Palette, a Singapore-based startup that uses machine learning and artificial intelligence to predict trends for food companies, announced it has raised $1.45 million Singapore dollars (~$1.1M USD) in seed funding. The blog e27 reported the news first, writing that the funding round was led by Decacorn Capital with participation from the Singapore government’s SGInnovate and AgFunder as well as existing investor Entrepreneur First.

According to Ai Palette’s website, the company uses “Artificial Intelligence and Machine Learning to draw insights from millions of data points to identify consumer needs in real time and combine it with the brand personality to create winning food product concepts.”

Using machine learning and AI to help food and CPG companies capitalize on emerging trends is an already crowded field. Companies like Spoonshot, Analytical Flavor Systems, Tastewise and Halla all use various implementations of machine learning and AI in this capacity.

The goal for all of these companies is to speed up the R&D process for food producers. The sooner a food trend can be spotted, the faster the process can be to get it to market. Additionally, AI allows companies to suck up even more data to provide more granular predictions based on things like regional preferences, or even come up with new flavor combinations that might not ordinarily be tried.

Ai Palette says it will use its new funding to scale up development and grow out its customer base across multiple markets.

The Food Tech Show: Mapping The Flavor Genome With Beth Altringer

Beth Altringer first became fascinated in flavor when she joined a competitive wine tasting league while in graduate school at The University of Cambridge.

While it had nothing to do with her field of study (product design and innovation), the very idea of breaking down the characteristics of wine and its flavor into highly descriptive and well understood categories was a revelation to Altringer, so much so she eventually began to think about the idea of applying this systematic and analytical approach to flavor to almost any type of food.

It was from there that the Flavor Genome Project was born, an initiative that “explores how components of flavor combine to create delightful multi-sensory, chemical, emotional, and cultural experiences.”  The goal of the project is to eventually create an “automated understanding of what people are intuitively searching for in a food or drink experience, regardless of the language they use to search for it, intelligently understanding flavor goals in context, and, ultimately, making it easier for people to discover experiences they are likely to enjoy.”

According to Altringer, the Flavor Genome Project is intended to be a platform that could be a foundation for other products, and the first of those product is a mobile game called Chef’s League.  The iOS game allows players to compete to master the usage of different flavor characteristics such as “salt, sweetness, acidity, fat, spice, and more.”

You can find out more about the Flavor Genome Project here and the Chef’s League game here. You can also learn about them from listening to my conversation with Beth on this episode of The Food Tech Show podcast. As always, you can listen to on Spotify, Apple Podcasts or wherever you get your podcasts, or you can download direct or just click play below.

Tastewise is the Latest Startup to Use AI for B2B Flavor Recommendations

Surprisingly, my eight-year-old’s current favorite toy is one of those old Magic 8 Balls that “predict” the future. Granted, most of his questions revolve around acquiring some Lego set, but he, like so many of us, want more certainty in our future.

Tastewise is a new startup that launched yesterday with a technology that aims to help restaurants and CPG companies better predict food trends using data and artificial intelligence (AI). According to the press announcement, “The platform analyzes billions of critical food and beverage consumer touchpoints to discover people’s real-life interactions with food including over 1 billion food photos shared every month, 153K restaurant menus across the US and over 1M online recipes.”

So Tastewise is looking at all those food pictures people are Instagramming and Tweeting about to see what is hip with the kids. It can also parse different ways items are described. For example, it will know that hamburgers, burgers and sliders are all basically the same thing. It takes all of this information and runs it through its algorithms to recommend new products on both a national and local level (what’s cool in Brooklyn may not be cool in Omaha).

I spoke with Co-Founder Alon Chen by phone, and he told me that with Tastewise, his clients can simply type in a food item like “hummus” and the software will crunch all the data and report back results of not only flavor information (ingredients people are adding to hummus), but also how people are using hummus (not just as a dip, but also as a spread).

Tastewise is offered as a SaaS product, and while specific subscription plans are being worked out, Chen said that they will always offer a free tier of results and a premium version for $299 a month. Exactly what results and insights are available to premium subscribers has yet to be determined.

The flavor-prediction sector is certainly hot like sriracha (though Tastewise says Zhoug is the next sriracha), as there are a number of other B2B players already in the market. Spoonshot and Analytical Flavor Systems both use AI to help companies predict and act quickly on food trends. Even spice company McCormick enlisted IBM’s Watson to help determine what tastes are on the horizon.

When asked about his competition, Chen said that Tastewise “is not a sensory platform.” Rather, his company is looking at what people are saying and the actions they are taking around food to develop consumer insight and intelligence that reflect what is happening and predict what specific foods and flavors will become hits.

Tastewise has raised $1.5 million in funding and has five employees. With CPG companies and restaurants all looking for any kind of edge over their competition, it doesn’t take a Magic 8 Ball to see that Tastewise has picked the right sector. Now we just need to see if it can beat out all the competition.

McCormick and IBM are Using AI to Develop Better-Tasting Spices

Today spice giant McCormick announced that it is partnering with IBM to create a research coalition to explore how artificial intelligence (AI) can improve flavor and food product development.

According to the press release, McCormick will use IBM Research AI for Product Composition to “explore flavor territories more quickly and efficiently” and “predict new flavor combinations from hundreds of millions of data points across the areas of sensory science, consumer preference, and flavor palettes.” In short: McCormick is applying IBM’s AI/machine learning power to their own taste data in an effort to develop better-tasting products more quickly — and with fewer duds.

The first product platform, called “ONE,” will debut mid-2019, and will include a set of one-dish Recipe Mixes, which I’m assuming are spice packets. The mixes are meant to season both a protein and a vegetable and come in flavors like Tuscan Chicken and New Orleans Sausage. McCormick is aiming to have them on grocery shelves by spring of this year.

To learn more about the ONE platform, we spoke with McCormick’s Chief Science Officer Hamed Faridi. “This technology uses multiple machine learning algorithms that are trained on information, including hundreds of millions of data points across the areas of sensory science, decades of past McCormick product formulas and information related to consumer taste preferences and palettes,” he told the Spoon. “What distinguishes the new system is its ability to learn and improve every time [it] is being used by our product and flavor developers.”

Unlike McCormick consumer-facing Flavorprint, which drew on recipe search histories to recommend new flavors and recipes, the ONE platform is purely internal. However, Faridi made it clear that the ONE platform would not replace consumer taste testing. “AI can’t taste flavors in the same way a human can,” he said. However, it will seriously up the speed of new product development. Faridi said that the AI system would let McCormick create new flavors up to three times faster, giving the company more agility so it could quickly develop products to take advantage of new dining trends.

Anytime the term “AI” — or the even trendier “machine learning” — is used by a Big Food company or fast food chain, it’s wise to take it with a grain of salt. As buzzwords, AI and machine learning can sometimes be more of a marketing gimmick than a value add.

That’s not to say that there aren’t several companies successfully leveraging AI to improve flavor. In fact, last year I wrote a piece predicting that services combining flavor and AI would be a new food tech trend. Analytical Flavor Systems has an AI-powered flavor prediction platform to help companies develop new food products with less trial and error. Plantjammer uses AI to help home cooks make better plant-based dishes. And Foodpairing applies AI to its flavor database to help professional chefs develop more innovative recipes. But these are smaller, tech-driven startups that have built their service based around AI from the beginning. For Big Food, AI is sometimes as much of a promotional tool as an actual service.

Since McCormick is working with IBM, its new platform seems more like a serious effort than, say, Dominos’. But is McCormick, as it states in the aforementioned press release, “ushering in a new era of flavor innovation and changing the course of the industry”? Probably not. But then again, I haven’t tried that New Orleans Sausage recipe mix.

Analytical Flavor Systems Raises $4M for its AI-Powered Flavor Prediction Platform

Analytical Flavor Systems (AFS), which uses artificial intelligence (AI) to help companies predict and personalize flavor for new food products, announced today that it has raised $4 million in Series A funding led Leawood Venture Capital and Global Brain. VentureBeat was first to report the news. AFS had previously raised an undisclosed amount of seed funding through Better Food Ventures and Techstars.

Food personalization, powered by advancements in AI and machine learning, is a big trend we’re following at The Spoon. Earlier this year we named AFS as one of our FoodTech 25 companies changing the way we eat, writing the following:

Analytical Flavor Systems’ AI-driven Gastrograph platform helps packaged food companies achieve greater success in a saturated food industry that has an over 80% failure rate. Gastograph moves CPG brands’ development process beyond traditional tasting panels; it surveys each product with a flavor profile engine that is predictive, anticipating how new foods will perform in different markets, over a long time horizon, and against various demographic archetypes. Food companies are struggling to launch new products in an era of rapidly shifting consumer tastes, and an AI-driven platform like Gastrograph gives big food a more accurate map with which to navigate into the future.

Think of Gastrograph almost like Flavor as a Service. Using data from “regular” people and professional tasters to power its analytical engine, Gastrograph can help food companies determine which flavors will be popular with different people or in different regions etc.

AFS Co-Founder and CEO, Jason Cohen spoke at our Smart Kitchen Summit in Seattle last month, and gave a presentation where he talked about personalization of food versus customization, and also provided a nice walkthrough of how AFS and Gastrograph works.

AI and Personalized Flavor

AFS told VentureBeat that it will use the money to build out the team and further develop its technology. The company’s fundraise comes at a good time, as it is among a raft of startups using AI to power flavor and food recommendations. Other players in the space include Spoonshot (formerly Dishq), Plantjammer, FoodPairing, and Flavorwiki.

Miele Invests in AI-Powered Cooking App Plant Jammer

German appliance giant the Miele Group has bought a minority stake in foodtech startup Plant Jammer. The Copenhagen-based company uses AI to suggest complimentary ingredients and build modular recipes. 

As I wrote back in February:

Vegetarian recipe-generating app Plant Jammer is out to help those with low kitchen confidence who want to cook healthy meals and reduce their food waste. The app creates custom recipes for users based off of whatever ingredients they have in their kitchen—then walks them through how to go from recipe to meal, step by step.

According to a press release, Plant Jammer’s algorithm and “choose your own adventure” approach to cooking is now being tested in Miele’s experimental kitchen. The two companies are working together to improve Plant Jammer’s app and test new ideas for kitchen equipment and interfaces.

Around the same time they took a minority stake in Plant Jammer, Miele also invested in German shoppable recipe startup KptnCook. And just a few weeks before that, they announced that they were partnering with MChef to create a food delivery service for customers who own Miele’s high-end Dialog oven.

My colleague Chris Albrecht posited that Miele’s investment in KptnCook could be used to gain valuable data on customer recipe preferences, then applied to MChef meal development. Down the road, their partnership could also help Miele get into a more direct version of shoppable recipes.

I imagine Miele could use Plant Jammer for a similar purpose. They would collect data on what types of recipes customers “jammed,” then use the information to develop plant-based dishes for MChef. But more importantly, they will use Plant Jammer to see if people prefer their modular recipe creation to the traditional recipe format.

“We set out to find if Plant Jammer’s approach could be a viable alternative to recipes for the next generation and the preliminary tests point to a roaring YES” Gernot Trettenbrein, Executive Director of Miele Venture Capital, said in the press release.

If they discover consumers prefer a more flexible, dynamic recipe creation process to following a list of instructions, that could inform their future plans to get into the shoppable recipe game. At the moment Plant Jammer doesn’t have shoppable recipe integration built into their app, but they do have a service where users can build a shopping list; it’s not hard to imagine them teaming up with an e-commerce company at some point.

Plant Jammer launched in early 2018 and has roughly 10,000 active users. Miele’s investment shows that they’re not sure exactly what the future of the recipe will be, but they’re willing to invest in a few to find out.

 

The Future of Flavor (Part I)

In this two-part series, guest contributor Chiara Cecchini explores how flavor may be understood, perceived, and valued in the future, based on insights gained from speaking with industry experts. Part I is more focused on the food system, while Part II delves into new flavor profiling technologies employing big data and AI.

The produce of today is being engineered for color, shape, yield, and shelf life, but it seems like the produce of the future will be optimized for flavor. Horticultural sciences professor Harry Klee is currently breeding a tomato for taste, based on analysis of flavor compounds in heirloom, wild, and modern tomatoes. This endeavor involved sequencing the genomes of over 400 tomato varieties, but his efforts also encompass part of a larger goal. Klee hopes that by understanding the chemical and genetic makeup of flavor in fruits and vegetables we can control the synthesis of flavor compounds and create better-tasting food.

In an age where the average supermarket tomato is watery and lackluster and where the generic pea no longer tastes like spring or the earth, an increased focus on flavor from the production side is most welcome. Peter Klosse, author of The Essence of Gastronomy: Understanding the Flavor of Foods and Beverages, asserts that this change may be driven by consumers’ frustrations with flavorless foods.  “Gradually, we’ve grown to changing our traditional agricultural systems to produce flavorless commodities,” Klosse states; according to Harry Klee in “Improving the flavor of fresh fruits: genomics, biochemistry, and biotechnology“, it is now generally accepted that the flavor quality of many fruits has significantly declined over recent decades. But blandness of products does not seem an issue because the food industry has found a way to solve the problem. This is done by incorporating salt, sugar, fats, and chemical additives to restore flavor that has been bred out of food.

Ultimately, a lack of value for produce’s flavor is where it all starts. Supermarkets, focused on getting food from producers to consumers in the most efficient, least costly means possible, want a consistent supply of consistent quality food. And while several food-tech companies are populating the market trying to provide solutions to meet this needs, Corporate farms, urged to meet industry demands, are forced to sacrifice seasonality and sustainability — and consequently, flavor.

“We have lost biodiversity,” Klosse says. “We have lost a lot of individual quality between farms and regions, we are losing varietal differences.” But consumers are starting to notice, and starting to care. Klosse believes innovation in this field should be focused on moving the food system towards regenerative agriculture.

Regenerative systems, involving maintaining biodiversity and using farming techniques that do not damage soil, are also flavor-rich. Food production today emphasizes efficiency and yield; but if the value of flavor — and subsequently the possibility of earning money by cultivating flavorful produce — is reintroduced, farmers can once again grow foods that are both flavorful and sustainable.

Klee’s research articulates the benefits of the older, more natural agricultural practices which Klosse promotes. His team has discovered that modern tomatoes lack the sweetness and rich flavors of heirloom breeds since flavor compounds have been lost over time; bred out as the genes responsible for producing the volatile flavor chemicals are neglected. Supermarket tomatoes are picturesque, hefty globes of firm red flesh. But bite into one and you’ll find that the tanginess, earthiness, and succulent sweetness associated with tomatoes are, well, absent. Beyond replicating Klee’s experiments by taste-testing a variety of tomatoes, Klosse claims we need palpable proof of concept for a regenerative system to convince the industry of its merits.

In short: we need real examples which you can see and touch. “Start small,” he suggests, “take a comprehensive region within the industry, from farmers to retail to consumers, committed to a new way of thinking, and demonstrate that regenerative systems work.”  In my opinion, if more people come to realize that said systems do in fact work, the food system of tomorrow may be one that combines future understandings and research on flavor compound interactions with past ecologically-friendly practices. If what we believe about flavor becoming increasingly prioritized by producers and consumers holds true, then the future of food is a truly appetizing one which we should look forward to.

Additional insights and contributions to this article were made by Audrey Chen

As with smart kitchens, the potential of technology and big data will be harnessed to provide product development solutions. To see two how innovations in digital flavor profiling and AI-powered analytics are revolutionizing the way companies and consumers alike view flavor, check back soon on The Spoon for the second installation of The Future of Flavor.

Video: The New Era of Personalized Flavor

Personalization was a big theme at Smart Kitchen Summit Europe: in nutrition, taste profiles for dining out, recipes, and more.

One of our hit panels ‘The New Era of Personalized Flavor’ explored this idea with Daniel Protz of FlavorWiki, Johan Langenbick of FoodPairing, and Alexandre Bastos of Givaudan, moderated by Luke Dormehl of Digital Trends.

The panelists talked about how millennials are demanding a more individual dining experience, personalization in the smart kitchen, and how flavor is king.

So what’s happening next? “Personalization is going to go more mainstream,” said Bastos. “Not just personalized flavors, but personalization in general.”

Watch the full video of the panel below.

Want to join us at the next Smart Kitchen Summit event in Seattle this October? You have two days left to snag Early Bird tickets.

FoodPairing Unveils FlavorID, A New Tool for Taste Personalization

Of the overarching trends that emerged at the first ever Smart Kitchen Summit Europe last week in Dublin, a big one was personalization. At the reception the evening before the event, FoodPairing wow-ed the crowd with a robot that made cocktails based on people’s individual taste preferences (spicy, sweet, floral, herbal, etc.). We at the Spoon were pretty impressed with the boozy results — definitely something we’d order again.

The next day, at a panel on the new era of personalization in food, FoodPairing founder Johan Langenbick unveiled a new solution for individualized food recommendation. Dubbed FlavorID, their service draws from over 8,000 different aromas and taste molecules, as well as 600 dietary descriptors, to develop a sort of flavor fingerprint for each individual.

Since they launched in 2009, FoodPairing has been developing a digital flavor database (the world’s largest, according to their press release) based on the aromatic profiles of over 2,500 ingredients. By synching this tech with individual consumer’s behavior — such as food experiences, preferences, and genetic predispositions — they can create a specific flavor identity (or “passport,” as their website calls it) for each user. “FlavorID was the missing link in our technology stack and portfolio of solutions,” said Langenbick.

This new tool will be used to create hyper-personalized recipe suggestions, menu recommendations, and meal plans linked to health goals and dietary restrictions.

Langenbick explained that they planned to partner with 3rd party apps, such as smart kitchen appliances, e-grocery services, mHealth apps and more, to bring FlavorID’s recommendations to the consumer. This will make it free for consumers to use. While FlavorID will be embedded in these other services, Langenbick said that they will also have their own mobile app so that consumers can access and control their personal data.

So where will this data come from? “The first input is, of course the 3rd party application in which FlavorID is embedded,” said Langenbick. But he and his team are also exploring other sources which do not require actual data input or questionnaires, such as purchased goods history, as tools to build out individual taste profiles.

FoodPairing is currently piloting a few use cases for FlavorID and told The Spoon that they expect to announce their first partnerships soon. Whether or not the service lives up to its lofty goals of granular recommendations right from the get-go, however, it’s a strong indicator that food personalization will become more and more present in our daily lives. And more and more companies, from Flavorwiki to dishq to PlantJammer, are leveraging this trend as a tool to better predict what we want to eat.

I could see a future where everyone has a flavor “fingerprint,” which restaurants, grocery e-commerce sites, and food delivery services can access to give uber-personalized recommendations, something like the personal food profiles Mike wrote about last year. Maybe someday Amazon will be able to look at this fingerprint to predict exactly what you want for dinner — and then have corresponding groceries, meal kits, or straight-up food delivery waiting for you on the kitchen counter when you get home from work. Services like FlavorID could play a large role in these futuristic meal journeys.