2012 NBA Draft Extravaganza: The Rankings

“It is always wise to look ahead, but difficult to look further than you can see.”

-Sir Winston Churchill

I am a self confessed NBA draft junkie. What does that mean exactly?

I know you have the Answer Tim

It means that I am always in the mood to write, project and speculate about the NBA draft. One of my key findings when looking at the draft is that all I needed to build an effective draft model to predict player performance was publicly available on the internet.

Stunning I know. Using this data, I built two models to predict the future performance of NBA draft picks (go here for the model build parts 1 & part 2 ). In very general terms the models use the available data to predict future performance for each player coming into the draft from college. Based on that prediction a ranking is done and a draft recommendation is generated.

It has performed at a very high level (see here for a full breakdown and here for the 2011 version).

In fact, It’s been so successful that I get a lot of requests for it in multiple platforms.

You’re welcome.

That’s the productivity projection for every draft prospect in Draft Expresses‘ delightful database. This year I’ve tried to cover every eligible prospect for whom any date is available. My plan as always is to continue to monitor these projections in the future.

Explanations and more wonderful stuff after the jump.

Let’s review the models real quick for any newcomers. I built two models specifically and I called them : Yogi and Booboo. They both use a series of publicly available factors (WS40, Age,Height, etc.) to project the player’s Wins Produced numbers for the duration of a player’s rookie contract in different ways. Yogi gives the go ahead for drafting at .095 projected WP48 and Boo Boo does the same at .067 WP48

A simple test for the models  is to look at correlation between the place the player was picked, where the models suggested picking him and actual rank by draft in terms of production. Draft order vs production shows minimal correlation with an R-square of about 5% . It jumps to 25% for the predicted production rank.

A more complex and interesting test is to look at:

  • The probability of landing a better than average player (>.090 WP48)
  • The probability of landing a good player (>.150 WP48)

If I do this for all picks by the Models as well as all draft picks and Model picks taken after the top 5 picks I get:

The models perform as well or better than the majority of lottery picks. The only real difference is superstar talent at the number one pick (which isn’t really an every year affair).

So to review, using publicly available data we built a model that picks draft winners at a 75% rate which is better in general than having the #1 pick in the draft and big winners at a 40% rate which is better than everything but the #1 pick.

But you’re not really here for the science are you? Let’s give you the money shot.

That’s all the prospects sorted by their Draft Express rankings of 6/25/2012. Just to make it easier for everyone. Let’s do some takeaways shall we?

That should tide you over for a bit.

Of course, there is more to come.




Comments are closed.