March Madness: The Quest For The Holy Grail

March Madness is in full swing and will have the world's attention for a few more days. As you could guess - most brackets have already busted. Louisville lost, UC Irvine won, and Duke barely weathered UCF's onslaught. 

 

via FanSided

Lots of skill, lots of adrenaline and lots of natural talents (including amazing physical talents).  Here is a picture of 7'6 Tacko Fall. Tacko still looks taller than his opponents even when kneeling. 

via UCF Basketball

The allure of March Madness is the same as gambling or trading.  These are all fertile grounds for emotion, biases, and statistics. 

The holy grail is mighty elusive in March Madness (as in most things)  ... For example, the odds of getting the perfect bracket is 1 in 9,223,372,036,854,775,808 (2.4 trillion based on a Duke Mathematician's formula that takes into account rank).  It's easier to win back-to-back lotteries than picking a perfect bracket. Nonetheless, I bet you felt pretty good when you filled out your bracket.

Here's some more crazy March Madness Stats: 

• 60 million tournament brackets were completed
• Companies expect $4 Billion of corporate losses due to employees tracking games
• The highest paid NCAA coach, Duke’s Mike Krzyzewski, makes a salary of $8,982,325
• It's expected to create $10 Billion in gambling (twice as much as the Super Bowl)

 

via Duke University

Feeding the Madness

"Not only is there more to life than basketball, there's a lot more to basketball than basketball." - Phil Jackson

 

In 2017, I highlighted 3 people that were (semi) successful at predicting March Madness. A 13-year-old who used a mix of guesswork and preferences, a 47-year-old English woman who used algorithms and data science (despite not knowing the game), and a 70-year-old bookie who had his finger on the pulse of the betting world.  None of them had the same success even a year later.

Finding an edge is hard - maintaining an edge is even harder.

That's not to say there aren't edges to be found. 

Bracket-choosing mimics the way investors pick trades or allocate assets. Some people use gut feel, some base their decisions current and historical performance, and some use predictive models. You've got different inputs, weights, and miscellaneous factors influencing your decision. That makes you feel powerful. But knowing the history, their ranks, etc. can be helpful in making an educated guess and they can also lead you astray. 

The allure of March Madness is the same as gambling or trading. As sports fans, it's easy to believe we know something the layman doesn't. We want the bragging rights of that sleeper pick, of our alma mater winning, of the big upset. 

You'd think an NCAA analyst might have a better shot at a perfect bracket than your grandma or your musical loving co-worker.

In reality, several of the highest-ranked brackets every year are guesses. 

The commonality in all decisions is that we are biased. Bias is inherent to the process because there isn't a clear cut answer. We don't have the answers to "who will win" and we don't have the answer to "what makes a perfect prediction". 

Think about it from a market efficiency standpoint. People make decisions on many factors - sometimes irrational ones - and that creates inefficiencies & complexities. It can be hard to find those inefficiencies and capitalize on them - but they're there to be found. 

In trading, that's where AI and advanced math come in - taking away our biases and identifying inefficiencies humans miss.

Can machine learning also help in March Madness?

“The greater the uncertainty, the bigger the gap between what you can measure and what matters, the more you should watch out for overfitting - that is, the more you should prefer simplicity” - Tom Griffiths

The data is there. Over 100,000 NCAA regular season games were played over the last 25+ years, and we generally have plenty of statistics about the teams for each season. There are plenty of questions to be asked on that data that may add an extra edge. 

That being said, people have tried before with mediocre success. It's hard to overcome the intangibles of sports - hustle, the crowd, momentum - and it's hard to overcome 1 in 9.2 quintillion odds. 

Two lessons can be learned from this:

1. People aren't as good at prediction as they predict they are.
2. Machine Learning isn't a one-size-fits-all answer to all your problems

 

Something to think about.