Putting food ads on a site devoted to recipes is a no-brainer, but Yummly is bringing some more complex data science to its platform than just keyword search ads. Yummly is applying the same algorithms it uses to parse recipes to its advertising, CEO David Feller said. So instead of popping off ads for boxed pastries whenever a user searches for “apple pie,” the engine can delve deeper.

An apple pie search might generate ads for the necessary ingredients such as for flour or apples, but it wouldn’t just select any variety of apples. Through recipe analysis, Yummly knows that apple pie is most often cooked using tart apples like Granny Smiths, so ads for red delicious apples just won’t do. Yummly can even infer what pairs well with a dish, Feller said.

“The data knows what we don’t know,” he said. “If somebody is looking for apple pie, Yummly knows that apple pie is complemented by ice cream, so we could give them ads for ice cream.”

Though those examples may seem rather simple, Yummly is launching with a limited number of advertisers and ad inventory. But the semantic search engine is growing quickly. In the last six months unique visitors on its site have nearly doubled, growing from 4 million in March to 7.5 million in September. That kind of growth won’t escape the notice of food brands. Feller thinks it won’t be long before Yummly can start delving down into very specific data to hone its ad targeting.

For instance, Yummly doesn’t just parse recipe ingredients. It extracts nutritional data and is even able to determine whether a dish or group of dishes is salty, sweet, savory or spicy from an analysis of its ingredients. Search options combined with histories generated by registered users tell Yummly about an individual cook’s preferences, whether he or she has food allergies, is on a fad diet or favors Asian over Mediterranean cuisines. Feller said all of these factors can be factored into ad targeting, and can be further refined by tracking seasonality of ingredients and even local weather conditions (stews and braises always go over well when its wet or cold).

The associations we make when craving food don’t always make logical sense. If I have a hankering chicken fried steak, it doesn’t mean I’m craving chicken or steak. Instead, I want comfort food, and Yummly would do much better to recommend me mac n’ cheese or meatloaf products and recipes. The ultimate goal, Feller said, is that Yummly will become wired the same ways are brains are to think about food

Related research and analysis from GigaOM Pro:
Subscriber content. Sign up for a free trial.

• What’s driving the next phase of the e-commerce evolution
• GigaOM Research highs and lows from CES 2013
• How HR can make the case for workforce analytics

Say Mmm is one of dozens of recipe aggregation and organization services sprouting up all on the Web and in app stores, but there’s a key difference between its approach and say a Paprika or a Pepperplate. Rather than require its customers to squirrel recipes behind the walls of a Web portal or app, Say Mmm thinks customers should take advantage of the Internet tools readily available for storing and sharing content, said the startup’s  founder Brian Hutchins.

“We don’t need to reinvent what’s already out there,” Hutchins said. “Rather than be a recipe dumping ground, our end goal is to make tools you can use with recipes that you store anywhere.”

Say Mmm is latching on to both Evernote and Facebooks’ APIs to draw out the recipes that users have saved within them. Say Mmm is then building applications such as meal planners and grocery list tools that organize that food data in ways Evernote and Facebook were never designed to do.

Using the Web as a cooking tool

There is a long list of recipe clipping apps and sevrice out there — in addition to Paprika and Pepperplate there’s KeepRecipes, Ziplist, HungrySeacow’s YummySoup and BigOven. They’re all designed to let you save recipes from the Web and then store and organize that cooking info in ways useful to home cook. For instance, they all have some sort of grocery list generation feature, can create weekly meal plans and often pair ingredients with nutritional data.

While these services are definitely attracting customers among more serious home cooks, the majority of cooks are saving their recipe ideas on the social media and productivity platforms they use every day.

A March survey by Exprian’s PriceGrabber, found that 70 percent of Pinterest account holders cited recipes as their most pinned items, beating out home decorating, crafts and shopping as the biggest source of inspiration among the network’s users. According to Springpad business development VP Jeff Janer, the note-taking service’s 3 million registered users have stored more than 1 million recipes through its clipping engine. A poll conducted of LifeHacker’s readers found that Evernote was by far the most used recipe aggregation tool – albeit among LifeHacker’s more tech-savvy readers.

The problem is that while all of those services are great at grabbing recipes from the Web, they don’t really let you do too much with that information (Springpad is an exception). Facebook and Pinterest don’t distinguish between the recipe you “like” or “pin” and any other object on the Web. Evernote allows you tag and search the recipes you save, but for the most part it’s saving the recipe as raw text in a note, not as a structured recipe file.

Adding structure to unstructured recipe data

Most of Say Mmm’s work so far has been on Evernote. Say Mmm accesses the contents of your Evernote cooking notepads, and then displays those recipes by their titles and their thumbnails in a Pinterest-like interface. From that interface you can sort recipes alphabetically or by tags, you can edit the recipes and photos (with changes reflected in Evernote), you can save a recipe to your Say Mmm recipe book and you can automatically generate shopping lists from the recipe ingredient lists.

Perhaps the most useful feature, however, is the meal planning function, which allows you to generate a schedule of dishes to cook by day or week and then save that plan as a note within Evernote. Say Mmm also allows you to create grocery lists within Evernote itself. By adding the tag “Say Mmm” to any Evernote recipe and then resynching, Say Mmm strips out recipes ingredients and generates a new grocery list organized by category (produce, dairy, etc.). You can even merge grocery lists into a single unified note with other tags.

On Facebook, the features are similar, except Say Mmm is extrapolating a lot of data from what little information Facebook actually stores. The service searches your Facebook news feed for recipes based on the links embedded in your news feeds and timeline. It then pulls metadata from those webpages and organizes those recipes into the same Pinterest-like interface, allowing you to sort dishes and generate meal plans as you would in the Evernote implementation. The Facebook features are still in closed beta, but Hutchins said he plans to launch them publicly this week.

“Evernote is already the perfect platform for organizing things, while Facebook is beautiful for sharing and social elements – there’s just no organization at all,” Hutchins said. In either case, Say Mmm isn’t trying to change what’s most valuable about the Facebook or Evernote. It’s just adding a structural layer that makes the recipe data they store more useful. As for Pinterest, Hutchins said, “the minute they open the API, I’ll be on it.

To be frank, Say Mmm still needs some work before its ready for mass consumer audience. If you’re looking for cutting edge Web design, it’s not here, and there are still some big pieces missing from its feature set. For instance, once you’ve saved a meal plan to Evernote, you can’t generate one unified shopping list from all of the recipes within it. You have to create a separate list from each recipe and then merge them.

Say Mmm, however, is still in the early stages of development, and being a bootstrapped venture, Hutchins is pretty much doing all of the work. A veteran of Grand Central Communications and Google, he left the search giant in 2010 to found Say Mmm and later joined Grand Central founder Craig Walker at food-focused startup Firespotter Labs, where he still works as a consultant. Say Mmm started out of side project that Hutchins is trying to turn into a commercial venture. He’s adding new functions gradually and eventually plans to launch mobile and tablet apps.

At this stage, your kitchen isn’t going to revolve around Say Mmm, but the company is definitely on to something. As I’ve written before, one of the biggest problems with using the Web as a cooking resource is its fragmentation. There’s no common format that would allow you to use any recipe with any service or app. Say Mmm has started building a framework to solve that problem.

Update: An earlier version of this post stated Hutchins started Say Mmm after joining Firespotter Labs. Rather, Hutchins founded Say Hmm and then joined Firespotter. 

Image courtesy of Flickr user gabriel amadeus.

Related research and analysis from GigaOM Pro:
Subscriber content. Sign up for a free trial.

• The state of cross-platform media measurement
• Social media in Q1: commerce and discovery dominated
• Controversy, courtrooms and the cloud in Q1