It's estimated that 21 million people will sign up for fantasy football in 2010. It's wildly popular, has become big business and is an accepted form of mainstream entertainment. If you haven’t heard, fantasy football is a game in which participants assemble an imaginary team of real-life players from the National Football League and compete against other “teams” by tallying and scoring points based on those players' actual statistical performance.
With the NFL season kicking off in a week, fantasy fanatics are scouring websites, reading magazines, and listening to “experts” on TV and radio in an attempt to gain an edge over their competition. And, there is but one goal – draft the best team by trying to predict which players are going to have the best statistics.
While many will rely on these traditional methods of identifying the top performers of 2010, others, like Hetal Thaker, a product manager at IBM and long-suffering fan of the Detroit Lions, turns to more “scientific” methods, by using predictive analytics software. Every year she steps into the fantasy football arena an unassuming competitor – and steps off the field at season end – a winner.
We talked to Hetal about how she creates a winning formula to crushing the men in fantasy football, the value of statistics and predictive analytics, and her strategy for success in 2010.
How long have you been playing fantasy football, and how did you initially get involved?
I love sports. My friends and I played flag football on Sundays and after the game we would go out and watch all the Sunday games with the boys. The boys had their own league and would never let the girls play so we started an all girls league in 1999. No surprise, it took no time before the boys wanted to be in the girls’ league.
What does it take to beat the “boys” in fantasy football? What characteristics do you need to possess?
Girls, at least the ones in our league, tend to be more analytical. They look at the data and read news stories. Some even make flash cards for the draft. Men tend to read a few things here and there, but think they know everything and end up drafting with their gut. That's not to say there isn't some degree of gut with the girls…also known as a football player's “cuteness factor.”
When did you realize that applying the use of predictive analytics would give you an edge?
I found myself going back to historical data, such as evaluating performance in previous seasons or injury history, and realized there are products and technologies I could use to not only automate the analysis all of this data, but gain a better probability – and predict – who would succeed.
How often do you win your league?
Before using predictive analytics, I won once in 11 years. By applying this technology, I've won three times in the last five years. Nothing like dominating the league and holding bragging rights.
Do the other members of the league know that you use predictive analytics? And if so, have they been convinced yet that data analysis can often trump gut?
Yes they know. They are definitely convinced, but not too pleased that I have a competitive edge. Whiners! It’s also not a bad thing to have expertise in math and statistics, which I highly recommend to anyone entering college or grad school.
Have your fellow players asked you for any of your tips?
Not so much tips, but they have asked how they can use predictive analytics to help them with their draft picks. Without giving away all my secrets, I've simply told them to look at the historical data, but more importantly, don't ignore the textual information, such as news coverage. One day when I retire my fantasy jersey I may even share my predictive models with the league.
What kind of data is most important to you when analyzing players you want to draft?
It’s really the textual data, such as injuries or past behavioral information, which can greatly improve my models and make them more accurate. Just like in the business world, combining structured information – transactional or demographic data – with attitudinal data – opinions, likes and dislikes – equates to having greater knowledge of a customer so an organization can create better marketing campaigns and targets. Textual information is very rich and provides deeper insight, but is also the hardest information to analyze, so it's often excluded. I had the good fortune of having a robust text analytics tool that allowed me to quickly analyze this data and categorize it. For example, I’m able to get the latest news reports on all the players right before my draft and quickly auto categorize the information into negative – critical injuries or suspensions – to positive – good preseason performance or good supporting cast. With these more accurate player profiles, I can now enter our draft with more confidence in who I think will yield the greatest output.
How have you improved your models over the past few years?
I've incorporated more metrics/attributes to determine future performance. I've also added in a new category – the “team factor” – that takes into account not only the player, but his supporting cast. This is very important because you can have the best wide receiver in the league, say Larry Fitzgerald of Arizona, but if he doesn't have a good quarterback passing to him, he's unlikely to have the fantasy value you would anticipate.
What simple rules can businesses learn from something as simple as fantasy football?
The power of data analysis. Any industry can benefit from using predictive analytics to improve marketing campaigns, identify fraud, reduce crime or find cures for diseases. The uses are endless, even fantasy football. But, in all reality, if I’m able to put together a winning strategy for football, then why aren’t more organizations – or my league members – taking advantage of this? We all want to win, so why not create the best possible competitive advantage and ensure you’re making the best and smartest decisions.
What tip/tricks can you give to other fantasy players to help them in their upcoming draft?
Keep the emotion out of it, and base your picks on the data and the statistics.
As we head into this year’s season, how are you feeling about your odds of winning?
I feel pretty good this year. I've spent a lot time collecting my data and preparing it for predictive modeling. Now, if you’ll excuse me, I need to go polish my league trophies. Game on, guys, game on!