The Data Science of Hockey Scoring

The Washington Post/Getty Images

Hockey is the coolest game on Earth.  At least, that is what the NHL reminds us about all the time. We hockey fans love seeing smart team plays, great passes, powerful slapshots, and flashy body checks. And even some limited fighting… But most of all, we love goals!  And we love and glorify the best goal scorers.  If you are a hockey fan, you will understand exactly what I am talking about. And this article is about those scorers.

Right now, the greatest goal scorer of all time is Wayne Gretzky, who reached a record of 894 goals.  The active players closest to him are Jaromir Jagr (766) and Alex Ovechkin (658). Jagr, who is a hero for many fans, is 47 now and semi-retired.  Ovi is 33 and is still going strong but, likely, has just a few years left for his high-scoring game (I hope to be proven wrong here!).

They, and a couple of others, have been the most elite scorers and we want to have more players like them in the future!  But, will we? Are we going to get many new superstar scorers capable of rivaling Gretzky, for example?  

Unfortunately, it is unlikely, unless the game is changed.  To show my point, I will use a bit of simple data analysis…

First, this is the list of the top 25 leading goal scorers per season in the history of NHL (source: NHL.com). Basically, these 25 players led the league in goal scoring ahead of everyone else.  Notice, the only active player on the list is Alex Ovechkin with 65 goals.

Alex’s best season was at 65 goals, which places him 23rd in history. Notice that Wayne Gretzky is at the top of the list with an incredible 92 and 87 goals.  Why do I say “incredible”? These numbers are unbelievably high in the modern hockey era. Think about it this way: during the last season, the entire team of Anaheim Ducks scored 196 goals in 82 games vs. 92 goals scored by just Wayne Gretzky alone in 80 games in the 1981-82 season.  

Now, is Alex Ovechkin with his best of 65 goals per season that bad?  Is every other modern hockey player so bad that they cannot even make it on this list?  Crosby? Malkin? McDavid? Kane? Others?

The answer is no.  This has less to do with the players and more with the years in the third column of the table above showing the time period during which they actually played and dominated the league.  A very simple data analysis should be able to illustrate this point. I am sure that somewhere on the nearly-infinite Internet this is already done and published many times… I just haven’t seen it and would like to check for myself.  And, for my analysis, I will use data from this source. 

The first plot below simply shows how many 50+ goal scorers there were each season, starting with the 1944-45 season.


I used the moving average (in red) to show the general trend. It goes up starting approximately in 1970, reaches its peak in 1992 (when 14 (!) players exceeded the 50-goal mark), and then declines. And we are now in 2019.  Almost at exactly where we started in 1944.

The next plot shows the same data but aggregated into 7-year bins. We can see more clearly that the NHL scoring reached its peak sometime between 1978 and 1992 and is now below the level of 1964-1971, in spite of many efforts to increase goal scoring in NHL.

What are these bars in green?  These are the time periods when Whayne Gretzky exceeded the 50 goal mark 9 times.  But, as you can see from the chart, this was a relatively normal thing then: in 14 years from 1978 to 1992, the 50-goal mark was exceeded… 106 times!  Or, there were 7.57 50-goal scoring players each year on average during that time period.  Let’s round it down to 7 per year. What a time that was! Look at this list of 14 players scoring more than 50 goals during one 1992-93 season… and the number in parenthesis shows how many times they have already done it. 

And now, let’s look at the last 7 NHL seasons (2013-2019): the 50-goal mark was exceeded just 5 times!  And four out of five times it was the same player who did it (hint: Ovi).  Five times in 7 years leaves us with a 0.71 50-goal scorer per year.  Let’s round to 0.7. Hence, we have 0.7 vs. 7.  An order of magnitude difference. Unfortunately, this is the new reality…  

My point here is that this simple analysis of historic trends suggests that the future of NHL hockey is not going to be a high-scoring one and we are not going to have many high-scoring forwards to enjoy…  One 50+ goal scorer per season should be expected going forward (and it is unclear what will happen after Alex retires at some point in the future).

I like the high-scoring game and feel that something has to be changed.  Smaller goalie pads? Wider or taller goals? Not sure… “Taller goals” is my personal suggestion.  Let’s add another six inches. Wouldn’t it be exciting to get back to the “standard” of 1978-1992? And, if this happens, Wayne’s oldest records might be, finally, at risk. 

And this should definitely help counter the general trend of having less and less unprotected space left in the goals, as nicely illustrated by the picture below (the original source of which is unknown to me):

Just look at the data and, for the sake of the game, update the rules to make scoring in our favorite sport more exciting. And give us more of the goal scorers we like so much.

This entry was posted in Amazing technology, data, and people, Analytics, data analytics, big data, big data analytics, data on the internet, data analytics meaning, Computers, Past, present, and future and tagged , . Bookmark the permalink.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

This site uses Akismet to reduce spam. Learn how your comment data is processed.