For the NCAA tournament this year, I simulated each game based on my predicted efficiency stats for each team (shooting percentage, shot selection, turnover rate, and offensive rebound rate). I submitted my work for Teamrankings.com’s college basketball blogging competition and I’m thrilled to announce that I moved on to the next round! I’m pretty excited for round 2 (deadline Tuesday at midnight). If you have a topic suggestion, let me know — bonus points for something semi-related to the game simulations I’ve been running.
Simply choosing the higher seed got 22 games right. RPI did slightly worse at 21, and I matched Sagarin at the top with 23 correct (71.9%). The problem? As evidenced by the potential wins columns, I lost my champion. Missouri battled Norfolk State the whole game and came out behind. Every method lost Missouri, Duke, and Michigan as round 2 predicted winners, and Missouri, Duke, or both as round 3 winners. I’ll need some help to catch up at the end, though. No other system had Missouri or Duke advance to the Final Four.
Specifically, where did I go right? Of my “upset locks” (over 60% probability), VCU and NC State came through, and Alabama nearly beat Creighton. It’s worth reminding at this point that 60% probability is not really a “lock.” In fact, I should only expect to get 2 out of 3 winners right, if I predict 60 to 70% odds for all three.
My other upset picks, at odds between 50 and 60%, were Texas over Cincinnati (Pomeroy and Sagarin had this one too), South Florida over Temple, St. Louis over Memphis, and Colorado State over Murray State. I got 2 of these 4 right, which is appropriate for the predicted odds. So, my upset picks went 4 out of 7 overall. St. Louis distinguished my bracket from just about everyone (Memphis was in Pomeroy’s top 10!).
I also missed a few upsets: 15 seeds Lehigh and Norfolk State (so long, Missouri), Xavier, Colorado, Purdue, and Ohio.
I reran the bracket predictions based on who won, and here are the new predicted odds for each region:
Teams in parentheses are teams that I predict to lose a close game, and when pushed through, they have favorable odds of advancing another round. For example, Indiana should give Kentucky a good challenge. If they win, they beat Baylor in 57% of my simulations as well.
In my initial bracket, one of Missouri’s toughest games was against Florida. Unsurprisingly then, I give Florida great odds to beat Norfolk State and 58.6% odds to beat Marquette. A Florida – Michigan State game in the elite eights looks like a dead heat (50.4% odds for Michigan State). The other regions look pretty similar to my initial predictions, though North Carolina’s road to the elite eight now looks especially easy (my poor Michigan Wolverines were their biggest challenge).
Here’s a new look at the final four:
With Missouri out, my new predicted winner is Kentucky, though their odds are only 56.1% in the championship game. If Ohio State gets through (I’m not adjusting for Fab Melo being ineligible for Syracuse, so I think that’s likely), I have them beating Kansas, and Kentucky’s odds are only 50.3% against them — almost dead even. Although Indiana’s odds over Michigan State are over 50%, they wouldn’t beat any of the likely teams from the other side.
And by the way, despite my good first round prediction rate, I am in last place in my family’s auction-style pool! Maybe it’s because I spent 9 out of 50 dollars on my hometown heroes (Michigan). Enjoy the second round!