Analyzing NHL Goalie Stats (03-04 07-08) Using the Self-Organizing - - PowerPoint PPT Presentation

▶

May 04, 2023 232 likes •426 views

Analyzing NHL Goalie Stats (03-04 07-08) Using the Self-Organizing Map By: Chuck Crittenden "In hockey, goaltending is 75 percent of the game. Unless it's bad goaltending. Then it's 100 percent of the game, because you're going to

SLIDE 1

Analyzing NHL Goalie Stats (03-04—07-08) Using the Self-Organizing Map

By: Chuck Crittenden

SLIDE 2

"In hockey, goaltending is 75 percent of the game. Unless it's bad goaltending. Then it's 100 percent of the game, because you're going to lose." ~ Gene Ubriaco (NHL forward)

SLIDE 3

Overview

l Problem l Hypothesis l Data l Self-Organizing Map l Resulting Map l Conclusion

SLIDE 4

The Problem

l NHL Goaltending Statistics by Team – (03-04 through 07-08) l Average Standings for each Team l Use Self-Organizing Map – Find natural clusters

SLIDE 5

Problem cont.

l Stats – GAA, SV %, DIFF l Standings and Levels

SLIDE 6

The Hypothesis

l Goaltending – Last Line of Defense l Levels will appear in the Resulting Map l Including DIFF

SLIDE 7

The Data

SLIDE 8

Data

l GAA – Goals Against Average

Goals Allowed ` Number of Minutes Played(1/60)

l SV% – Save Percentage

Goals Allowed Shots Allowed

l DIFF – Goal Differential

DIFF = Goals Scored – Goals Allowed

SLIDE 9

The Algorithm

l Self-Organizing Map (SOM) – Artifical Neural Network l Clusters in 2-dimensional map

SLIDE 10

What is Needed?

l A .bat file containing the reference to the

executables and the specifics of the map.

l The executables randomly initialize, run the

algorithm, and calibrate the label onto the points.

l som_mapper.exe

SLIDE 11

Initial Map

l Randomly intialized. l Each team (p) compared to each point on

the map (q) with Euclidean distance.

l Whichever point the specific team is closest

to.

l That point is trained accordingly. l Other points around it are also trained,

just not as much.

SLIDE 12

SOM

l Process repeats for a set number of times. l The labels are pasted on to each instance. l The Map is made.

SLIDE 13

The Result

l 15x15 Map

SLIDE 14

Result

l Layers l Levels l Overlaps l Corners l Columbus l Big Names l Effect of

Lockout

SLIDE 15

Standings

SLIDE 16

Conclusion

l Able to cluster levels l Extreme teams in corners l DIFF makes a difference l Goaltending makes a difference.

SLIDE 17

"In hockey, goaltending is 75 percent of the game. Unless it's bad goaltending. Then it's 100 percent of the game, because you're going to lose." ~ Gene Ubriaco (NHL forward)

SLIDE 18

Summary

l Problem l Hypothesis l Data l Self-Organizing Map l Resulting Map l Conclusion

SLIDE 19

Sources

Aleshunas, John. Retrieved Apr. 17, 2008. “Self-Organizing Map (SOM)” from: http://mercury.webster.edu/aleshunas/MATH%203210/MATH%203210%20Source%20Code%20and%20Executables.html Goaltender’s Annex. Retrieved May 5, 2008. Ubriaco Quote from: http://www.angelfire.com/sk/goalieannex/quotes02.html NHL.com. Retrieved Apr. 16, 2008. “Goalie Statistics and Team Standings” from: http://www.nhl.com/nhlstats/app Yahoo Sports. Retrieved Apr. 16, 2008. “Goalie Statistics and Team Standings” from: http://sports.yahoo.com/nhl/teams/___/stats (Replace ___ with each team’s abbreviation).

Wikipedia. Retrieved Apr. 17 2008. “Stepping through the Algorithm” from:

http://en.wikipedia.org/wiki/Self-organizing_map - Stepping_through_the_algorithm

Wikipedia. Retrieved May 1, 2008. “List of Stanley Cup Champions” from:

http://en.wikipedia.org/wiki/List_of_Stanley_Cup_champions#NHL_champion

Wikipedia. Retrieved May 6, 2008. “Euclidean Distance” from:

http://en.wikipedia.org/wiki/Euclidean_distance