We’ve heard a lot about draft year scoring and how it predicts NHL performance - but that's not where a prospect's pre-NHL development usually ends. So the question is, do subsequent seasons such as a player’s performance in his draft+1 year help forecast future NHL success or failure?
August 14 2013 09:29AM
By: Pierce Cunneen
Most readers here may be familiar with the Zone entry project. For those who aren't, check out this article by Eric T from NHL numbers. Short version: a group of bloggers for the past few years have taken it upon themselves to track Neutral zone performance for several teams.
August 08 2013 02:20PM
If you've been following my few posts here you will know that I am studying Machine Learning for my masters in Computer Science and I am using those techniques and applying them to hockey analytics. I have found some pretty interesting stuff. Some of my first few posts I wrote here (namely this one and this one) were based off some of my academic research. I have since turned those into an academic paper that was accepted to a Sports Analytics paper.
You can read it: here
The conference it will be presented at is the European Conference for Machine Learning. Specifically at the Sports Analytics and Machine Learning workshop on Friday, 27 September in Prague, Czech Republic.
If you are near Prague at the end of sepember and want to talk shap, drink a Pilzen and check out a local KHL/Czech hockey game, then send me a message via twitter. I will be there for the week.
August 08 2013 09:28AM
Whether it's on a per-game basis or season-to-season, we spend an awful lot of time looking at shot differentials to get a better feel for the strength of a hockey team. Unfortunately, the hockey blogosphere doesn't actively track rolling numbers at the team-level, a study that could give us a better handle of teams truly gaining/fading over the course of a season.
After the jump, a compilation of rolling team Corsi for the Western Conference during the 2012-2013 season.
August 06 2013 10:02AM
In my last article I was looking at prediction limits for machine learning and sports. More specifically I answered the question of how much of the standings are because of luck (aka, random chance, stochastic process etc). By using classic test theory and looking at the variance of the observed win percentage over 7 seasons between 2005-2006 and 2011-2012 and comparing it to a theoretical league where the level of teams talents are normally distributed. From this we were able to conclude that luck explains ~38% of the variance in the standings.
This is interesting, much higher than one might initial think, but it makes sense and I will discuss this further on. As my area of research is in Machine Learning and using Machine Learning to make predictions in hockey. What I am curious today is to answer the question, is there a theoretical limit to predictions we can make in hockey?