Finding the Perfect Wine Pairings with Graph Analytics

AlyssaIf there’s anything I have learned at YarcData, it’s that graphs are everywhere. Some are obvious, as seen in social networks, but others take a bit of creativity to comprehend.

Case in point: As a Bay Area resident, I love heading to Napa for wine tasting. On a recent trip to celebrate a friend’s birthday, one particular winery gave us an excellent lesson on how food like cheese and chocolate enhances a varietal’s flavor. We also learned that the coffee drinkers among us preferred red over white, because they were more accustomed to bitterness. The tasting demonstrated that palettes are more nuanced than we thought and that what we enjoy drinking is heavily influenced by what we pair our drinks with.

Overwhelmed by all the combinations that could exist between various food and drink, I decided to investigate whether any researchers developed this information into a graph. I discovered that in 2011, researchers Yong-Yeol Ahn, Sebastian E. Ahnert, James P. Bagrow, and Albert-Laszlo Barabasi, published a paper about the ‘flavor network,’ which they constructed by combining a list of flavor compounds and three online recipe datasets (two from America, one from South Korea). Since then, they have added further datasets, a process that is much easier and faster when using graph analytics technology.

Scientific American discussed their findings, and created an interactive graph of the flavor network. Each node represents a different ingredient and the edges are the connections between them in North American and Eastern cuisines. The size of the node correlates to that particular ingredient’s prominence in the pool of recipes.

The results? Ahn and his colleagues found that the food pairing hypothesis, which states that ingredients of shared flavor compounds go well together, rings more true in Western cuisines. Eastern cultures tend to prefer contrasting flavors over complimentary ones. This is why American recipes frequently include milk, butter, egg, and wheat, whereas Asian recipes employ flavors that pack more of a punch, like cilantro and soy sauce.

The flavor network is more than figuring out that bleu cheese and dark chocolate make an excellent pairing. It holds a wealth of knowledge that can be applied to everything from personal diets (What’s a delicious vegan alternative to honey?) to corporate menu planning (What ingredients will make my salads most profitable?).

Moreover, the impact that can be derived by clustering entities by attributes is not restricted to the food and drink industry. By using graph analytics to discover relationships between clusters, financial institutions can target their VIP investors, sports teams can optimize their lineups, and retailers can offer more personalized recommendations to their customers.

As for me, I can’t wait to head back up to wine country and put the flavor network to the test—in the name of graph analytics, of course!

Sochi or S—Oh no!—chi?

AlyssaI love the spirit surrounding the Olympic Games; in fact, I’ve been fascinated by their cultural significance ever since I learned about first Olympics in Ancient Greek history. A sporting event so important that the ancients dated their calendar around it!

For better and worse, a lot has changed since 776 BCE. Today marks the Opening Ceremonies of the 2014 Winter Olympics in Sochi, Russia, and as much as I would rather enjoy the festivities, it’s clear that this Olympics has been tarnished by controversies as serious as the violation of human rights and the mass killings of stray dogs to as laughable as missing doors on hotel bathroom stalls.

If anyone claims that the Olympics isn’t one of the biggest big data problems right now, then I say that he’s dizzy from too many luge runs. Here’s a snippet of stats on the 2014 games:

  • 98 events in 15 winter sport disciplines, including new competitions like women’s ski jumping and snowboard slopestyle
  • Over 2,800 athletes from 88 participating nations
  • A budget of over US$51 billion, the most expensive Olympics in history

Thus, data will be collected and analyzed from a plethora of sources—athlete performance, social media engagement, financial transactions, and security surveillance, to name a few. Security is, of course, the most pressing concern in Sochi, since the location is such a prime target for terrorist activity. Just today a plane landed in Turkey due a bomb threat by an alleged hijacker intent on flying to Sochi.

YarcData has demonstrated that all of these big data issues are best represented as graphs so as to analyze not only the data points, but also the relationships between them. This way, Sochi can provide real-time updates on sports stats, prevent fraud and identity theft, and protect the lives of everyone involved in the games.

So here’s to a safe, exciting Winter Olympics! And to quote from a tale about a much more morbid games, “May the odds be ever in your favor!”

Protect Your Customers’ Identities—And Their Peace of Mind

AlyssaSometimes I find myself surprised that I’m working for a big data analytics company, given the types of messages I received from my father growing up. He holds onto his privacy with an iron grip, refusing to pay bills online and only recently submitting to the convenience of using a debit card at an ATM.

I, on the other hand, don’t bat an eyelash when it comes to joining the latest social network or posting on my book blog. I access breaking news on Twitter, network on LinkedIn, and save a ton of money on stamps with automatic bill pay.

However, I recognize the risks of a digital lifestyle, especially in the aftermath of the Target and Neiman Marcus cyber-attacks. Even though your information is better protected online, you can’t help but wonder whether anyone is really safe. Every day you’re in danger of losing your identity to password hacks, phishing scams—even stolen Snapchat photos.

Despite my father’s warnings of putting personal information in the public eye, I’m now harnessing the data that I gain from others via social media, web behavior, and email marketing. And it’s precisely because I work at YarcData that I’m not paralyzed with fear. The silver lining to this chaotic cloud is that tech companies are finding better and faster ways to prevent future cyber-attacks.

Tim White, our Global Head of Government and Intelligence, contributed an op-ed to The New York Times in which he discusses why cybersecurity continues to be threatened despite the multi-billion dollar investment on strengthening its services.

His extensive experience working with cyber analysts in both the government and private sectors has demonstrated that it’s not about throwing more money at the problem; it’s about using that money wisely to arrange and analyze these massive volumes of data.

“What we need, then,” White stated, “is not necessarily more money or information, but a better way of knowing what it means—of interpreting the data to discover an unknown attack as it happens or, even better, anticipate the next attack.”

White explains why graph analytics is the solution to this challenge: by moving away from a tabular method of analyzing data to one that creates a vast visual network of objects, it’s much easier to look past all the noise and pinpoint suspicious patterns.

Technology also must perform at an unmatched speed and scale, because it’s worthless if attacks are only discovered months after the fact. The key to this is ingesting all data in memory and highly parallel processing to analyze the entire graph rather than a mere subsection of it.

Cybersecurity is obviously not just an issue for government agencies. For their customers’ sakes, I hope that all major retailers like Target—as well as financial institutions, social media sites, and the like—take a hard look at where their analytic efforts are falling flat. Because if recent events have taught us anything, it’s that losing your identity is not nearly as devastating as losing your trust in the people with whom you do business.

For more information on YarcData’s cybersecurity solution, watch our interview with Tim White below.