According to the American Gaming Association 40 million Americans are expected to have filled out some 149 million brackets in 2019, with about $8.5 billion being wagered throughout the tournament.

Like many offices, MGMT3D and EBM Software get a friendly little NCAA tournament pool going every year. As a bunch of certified number-crunching data geeks, you can bet bragging rights are a serious prize in this office. And true to form, several members of the MGMT3D team turned to advanced statistical models to help project our brackets.

One fantastic piece that made the rounds in our office offered an incredibly deep 28-page dive into rankings across predictive metrics, S-Curve positioning to identify over and under-seeded teams, coach performance against seed expectations, and many more fascinating statistics and trends.

Another favorite around the office is the model used by Nate Silver’s fivethirtyeight.com. In addition to providing a round-by-round statistical probabilities of each team’s path to the national championship, fivethirtyeight will also be providing live win probabilities during the course of the games. If you haven’t seen their NCAA tournament page, it’s definitely worth a visit.

Perhaps most interestingly, Adobe got in on the action offering deep-dive data and round-by-round picks to promote Adobe Analytics via their #HacktheBracket campaign. According to Adobe, their bracket finished in the 98th percentile last year, which is certainly good enough to win most office pools.

Adobe Analytics compiled statistics from 56,000 college basketball games into 3.5 million rows of data, and has opened the door to anyone and everyone to give their big data Analytics tools a try when assembling their brackets.

It has been well-proven that big data can have massive value in sports, and the NCAA tournament seems to be the one time a year millions of Americans who never really touch it decide to put their statistician hat on and start crunching the numbers.

They say your chances of scoring a perfect bracket are about 1 in 9.2 quintillion. With so much data available, how come everyone isn’t doing better on their brackets?

Well, the fact still remains: pulling valuable insight from big data can be a big challenge.

There are no strict limits defining what big data is. It’s simply defined as any data set that is too large to be processed through traditional methods. That means it’s inherently difficult to draw useful conclusions without the right toolset. But if you can extract those insights, you have some incredibly powerful information in your hands.

This is a problem we help clients work through every day. They’re trying to better understand an aspect of their business, but don’t quite know how to get there. Big data on its own isn’t worth much, but if we help them slice and dice it in a meaningful way and view it through the proper frame-of-reference, it can be a game changer.

You have to have context to extract value. You need to be able to look at things in different ways to ensure you’re operating off of facts, not assumptions. You need to be able to bring together different data sets to understand your benchmarks and potential variables.

Partnering with MGMT3D and EBM Software lets you pull these disparate data sets together into a single repository where you can draw out useful insights, build forecasts and scenarios, and drill down into the data to understand why things are the way they are. In other words, we help you turn it into something actionable instead of a guessing game with 1 in 9.2 quintillion odds.

Once we’ve done that, it’s not just big data anymore. It’s informed knowledge.