SlideShare a Scribd company logo
1 of 25
Download to read offline
DO NOT REDISTRIBUTE WITHOUT PERMISSION OF ARI KAPLAN




                                                                         Ari Kaplan
                                                                        312-513-0091
12/10/2012                  Property of Ari Kaplan. Copyright 2012   Ari@AriBall.com
“What’s more important than the will to win is
   the will to PREPARE to win” – Coach Wooden




12/10/2012          Property of Ari Kaplan. Copyright 2012   2
Prepare to win!




12/10/2012   Property of Ari Kaplan. Copyright 2012   3
Seek open-ended questions…
      Why is a batter struggling?
      Why aren’t we selling as much as we
       thought?
      Is an injury affecting a pitcher’s mechanics?
      What would happen if we acquired this
       company?
      What should our next steps be?

             …then give actionable answers
12/10/2012             Property of Ari Kaplan. Copyright 2012   4
Apply analytical models again
and again to get answers
      Above the Field
            Player forecasting
            Economics of contracts
            Roster modeling
            Trade-deadline analysis
            Drafts
      On the Field
            Game Preparation: Advance Scouting
            Pro-Scouting
            Amateur Scouting
            International Scouting
            Player Development
            Injury prediction and management

12/10/2012                    Property of Ari Kaplan. Copyright 2012   5
Multistructural Data Sources
(externally collected)
                                    Statistics (MLB, STATS,
                                     AriBall, Inside Edge)
   Play-by-play (MLB
                                                                                   Defense (BIS)
   Advanced Media)




        Contracts & Financials                                             Pitch & hit mechanics
           (eBIS, Stadium                                                 (SportVision, Trackman)
             operations)




12/10/2012                       Property of Ari Kaplan. Copyright 2012                             6
Multistructural data sources
(internally collected)
                                          MiLB Coach Reports

         Organizational Video                                                  Pro-Scouting Reports




                                                                                        Amateur Scouting
   Injury & Medical
                                                                                            Reports




             International Scouting                                            Advance Scouting
                    Reports                                                        Reports




12/10/2012                            Property of Ari Kaplan. Copyright 2012                          7
Understand and manage risks




12/10/2012   Property of Ari Kaplan. Copyright 2012   8
Analytics for past, present, future
      Learn these three points: What has
       happened? What is happening? What
       will happen?




12/10/2012          Property of Ari Kaplan. Copyright 2012   9
Find actionable patterns in the data




                                                 Barry Zito’s Fastball
                                                 release points come down
                                                 and over a foot




12/10/2012   Property of Ari Kaplan. Copyright 2012                   10
Find events preceding a
business issue
Track consistency and deception of release points and velocity as the season
progresses. See how injuries, trades, or assignments from the Minors affect mechanics.




12/10/2012                    Property of Ari Kaplan. Copyright 2012            11
Predict what might happen from
time-series information




12/10/2012   Property of Ari Kaplan. Copyright 2012   12
Refocus workers from the mundane
to the strategic
What happened? What is happening? What will
happen?
      Scoutable™ reports: based on full coverage of every
       pitch, every game. The reports are presented in the same
       formats that many scouts and organizations use today.
        Habits: threw FB whenever there was a 3-ball count. Never threw
             consecutive pickoff moves.

        Strengths: changeup had a big fading action. Kept first-pitches
             down 48% of the time (25% was avg). Plus control of his FB.

        Summary: Threw FB 91-94 (34% of all pitches), cutter 88-91 (12%),
             sinker 91-94 (28%), curveball 75-78 (13%), changeup 85-87 (13%)

        Last game compared to before: threw sinkers 16% less often and
             cutters 14% more often

12/10/2012                         Property of Ari Kaplan. Copyright 2012   13
Find the “signal from the noise”
Example: is a player’s hurt knee affecting their swing?

             Before injury: white                                          After injury
         circles are hits, green are
                   misses




12/10/2012                        Property of Ari Kaplan. Copyright 2012                  14
Use intelligence to find
opportunities
• Where did a pitcher generate outs? What pitch types and locations? Below shows
  FB up and slider low/away.
• Where did he allow hits? FB inner half, BB up in zone outer half.
• These reports can be for pitcher/batter matchups, across years, and much more




12/10/2012                   Property of Ari Kaplan. Copyright 2012         15
The “Human Element”: Quantifying
 the subjective
Which umpires made the most                    What was Hunter Wendelstedt’s strike zone?
frequent bad calls?




Umpire Strike Zones
  12/10/2012                  Property of Ari Kaplan. Copyright 2012               16
Use intelligence to better “defend”
yourself




12/10/2012   Property of Ari Kaplan. Copyright 2012   17
Competition: put yourself in their shoes




12/10/2012     Property of Ari Kaplan. Copyright 2012   18
12/10/2012   Property of Ari Kaplan. Copyright 2012   19
The future of batter analysis
 Contact point                         Elevation angle
 Speed off bat                         Field direction




                                                           Image source: Sportvision




12/10/2012        Property of Ari Kaplan. Copyright 2012                20
The future of batter analysis




Image source: Sportvision

     12/10/2012             Property of Ari Kaplan. Copyright 2012   21
The future of fielding analysis




Image source: Sportvision

     12/10/2012             Property of Ari Kaplan. Copyright 2012   22
The future of fielding analysis
The pivot
      6-4-3 Double plays
   Play #                       Time from SS to 2B*                                          Pivot time**
             1                                  .60                                              .60
             2                                  .40                                              .40
             3                                  .27                                              .60
             4                                  .53                                              .40
             5                                  .53                                              .40
             6                                  .53                                              .53
             7                                  .67                                              .33
                                                                                                       Image source: Sportvision
  * From SS releasing the ball to 2B getting the ball
  ** From 2B getting the ball to 2B releasing the ball



12/10/2012                                          Property of Ari Kaplan. Copyright 2012                               23
Create the ULTIMATE game-plan




Image source: Sportvision



     12/10/2012             Property of Ari Kaplan. Copyright 2012   24
Keynote: Cross Industry Lessons from Moneyball Analytics

More Related Content

More from Teradata Aster

What Makes A Great Data Scientist?
What Makes A Great Data Scientist?What Makes A Great Data Scientist?
What Makes A Great Data Scientist?Teradata Aster
 
Practical Applications of Visual Analytics
Practical Applications of Visual AnalyticsPractical Applications of Visual Analytics
Practical Applications of Visual AnalyticsTeradata Aster
 
Trust and Influence in the Complex Network of Social Media
Trust and Influence in the Complex Network of Social MediaTrust and Influence in the Complex Network of Social Media
Trust and Influence in the Complex Network of Social MediaTeradata Aster
 
Turning Big Data to Business Advantage
Turning Big Data to Business AdvantageTurning Big Data to Business Advantage
Turning Big Data to Business AdvantageTeradata Aster
 
Big Brands Meet Big Data – The Newest Innovator’s Dilemma
Big Brands Meet Big Data – The Newest Innovator’s DilemmaBig Brands Meet Big Data – The Newest Innovator’s Dilemma
Big Brands Meet Big Data – The Newest Innovator’s DilemmaTeradata Aster
 
Simplifying Big Data Analytics for the Business
Simplifying Big Data Analytics for the BusinessSimplifying Big Data Analytics for the Business
Simplifying Big Data Analytics for the BusinessTeradata Aster
 
Evaluating Big Data Predictive Analytics Platforms
Evaluating Big Data Predictive Analytics PlatformsEvaluating Big Data Predictive Analytics Platforms
Evaluating Big Data Predictive Analytics PlatformsTeradata Aster
 
Technology Strategies for Big Data Analytics,
Technology Strategies for Big Data Analytics, Technology Strategies for Big Data Analytics,
Technology Strategies for Big Data Analytics, Teradata Aster
 
Hadoop - Now, Next and Beyond
Hadoop - Now, Next and BeyondHadoop - Now, Next and Beyond
Hadoop - Now, Next and BeyondTeradata Aster
 
From Data Science to Business Value - Analytics Applied
From Data Science to Business Value - Analytics AppliedFrom Data Science to Business Value - Analytics Applied
From Data Science to Business Value - Analytics AppliedTeradata Aster
 
Solving the Education Crisis with Big Data
Solving the Education Crisis with Big DataSolving the Education Crisis with Big Data
Solving the Education Crisis with Big DataTeradata Aster
 
Using SQL-MapReduce for Advanced Analytics
Using SQL-MapReduce for Advanced AnalyticsUsing SQL-MapReduce for Advanced Analytics
Using SQL-MapReduce for Advanced AnalyticsTeradata Aster
 
SAS aster data big data dc presentation public
SAS aster data big data dc presentation publicSAS aster data big data dc presentation public
SAS aster data big data dc presentation publicTeradata Aster
 
Utilizing Aster nCluster to support processing in excess of 100 Billion rows ...
Utilizing Aster nCluster to support processing in excess of 100 Billion rows ...Utilizing Aster nCluster to support processing in excess of 100 Billion rows ...
Utilizing Aster nCluster to support processing in excess of 100 Billion rows ...Teradata Aster
 
20100506 aster data big data summit - microstrategy (shareable)
20100506   aster data big data summit - microstrategy (shareable)20100506   aster data big data summit - microstrategy (shareable)
20100506 aster data big data summit - microstrategy (shareable)Teradata Aster
 
Mastering MapReduce: MapReduce for Big Data Management and Analysis
Mastering MapReduce: MapReduce for Big Data Management and AnalysisMastering MapReduce: MapReduce for Big Data Management and Analysis
Mastering MapReduce: MapReduce for Big Data Management and AnalysisTeradata Aster
 

More from Teradata Aster (18)

What Makes A Great Data Scientist?
What Makes A Great Data Scientist?What Makes A Great Data Scientist?
What Makes A Great Data Scientist?
 
Practical Applications of Visual Analytics
Practical Applications of Visual AnalyticsPractical Applications of Visual Analytics
Practical Applications of Visual Analytics
 
Trust and Influence in the Complex Network of Social Media
Trust and Influence in the Complex Network of Social MediaTrust and Influence in the Complex Network of Social Media
Trust and Influence in the Complex Network of Social Media
 
Turning Big Data to Business Advantage
Turning Big Data to Business AdvantageTurning Big Data to Business Advantage
Turning Big Data to Business Advantage
 
Big Brands Meet Big Data – The Newest Innovator’s Dilemma
Big Brands Meet Big Data – The Newest Innovator’s DilemmaBig Brands Meet Big Data – The Newest Innovator’s Dilemma
Big Brands Meet Big Data – The Newest Innovator’s Dilemma
 
Simplifying Big Data Analytics for the Business
Simplifying Big Data Analytics for the BusinessSimplifying Big Data Analytics for the Business
Simplifying Big Data Analytics for the Business
 
Evaluating Big Data Predictive Analytics Platforms
Evaluating Big Data Predictive Analytics PlatformsEvaluating Big Data Predictive Analytics Platforms
Evaluating Big Data Predictive Analytics Platforms
 
Technology Strategies for Big Data Analytics,
Technology Strategies for Big Data Analytics, Technology Strategies for Big Data Analytics,
Technology Strategies for Big Data Analytics,
 
Hadoop - Now, Next and Beyond
Hadoop - Now, Next and BeyondHadoop - Now, Next and Beyond
Hadoop - Now, Next and Beyond
 
From Data Science to Business Value - Analytics Applied
From Data Science to Business Value - Analytics AppliedFrom Data Science to Business Value - Analytics Applied
From Data Science to Business Value - Analytics Applied
 
Solving the Education Crisis with Big Data
Solving the Education Crisis with Big DataSolving the Education Crisis with Big Data
Solving the Education Crisis with Big Data
 
Using SQL-MapReduce for Advanced Analytics
Using SQL-MapReduce for Advanced AnalyticsUsing SQL-MapReduce for Advanced Analytics
Using SQL-MapReduce for Advanced Analytics
 
SAS aster data big data dc presentation public
SAS aster data big data dc presentation publicSAS aster data big data dc presentation public
SAS aster data big data dc presentation public
 
Utilizing Aster nCluster to support processing in excess of 100 Billion rows ...
Utilizing Aster nCluster to support processing in excess of 100 Billion rows ...Utilizing Aster nCluster to support processing in excess of 100 Billion rows ...
Utilizing Aster nCluster to support processing in excess of 100 Billion rows ...
 
comScore
comScorecomScore
comScore
 
20100506 aster data big data summit - microstrategy (shareable)
20100506   aster data big data summit - microstrategy (shareable)20100506   aster data big data summit - microstrategy (shareable)
20100506 aster data big data summit - microstrategy (shareable)
 
Sqlmr
SqlmrSqlmr
Sqlmr
 
Mastering MapReduce: MapReduce for Big Data Management and Analysis
Mastering MapReduce: MapReduce for Big Data Management and AnalysisMastering MapReduce: MapReduce for Big Data Management and Analysis
Mastering MapReduce: MapReduce for Big Data Management and Analysis
 

Keynote: Cross Industry Lessons from Moneyball Analytics

  • 1. DO NOT REDISTRIBUTE WITHOUT PERMISSION OF ARI KAPLAN Ari Kaplan 312-513-0091 12/10/2012 Property of Ari Kaplan. Copyright 2012 Ari@AriBall.com
  • 2. “What’s more important than the will to win is the will to PREPARE to win” – Coach Wooden 12/10/2012 Property of Ari Kaplan. Copyright 2012 2
  • 3. Prepare to win! 12/10/2012 Property of Ari Kaplan. Copyright 2012 3
  • 4. Seek open-ended questions…  Why is a batter struggling?  Why aren’t we selling as much as we thought?  Is an injury affecting a pitcher’s mechanics?  What would happen if we acquired this company?  What should our next steps be? …then give actionable answers 12/10/2012 Property of Ari Kaplan. Copyright 2012 4
  • 5. Apply analytical models again and again to get answers  Above the Field  Player forecasting  Economics of contracts  Roster modeling  Trade-deadline analysis  Drafts  On the Field  Game Preparation: Advance Scouting  Pro-Scouting  Amateur Scouting  International Scouting  Player Development  Injury prediction and management 12/10/2012 Property of Ari Kaplan. Copyright 2012 5
  • 6. Multistructural Data Sources (externally collected) Statistics (MLB, STATS, AriBall, Inside Edge) Play-by-play (MLB Defense (BIS) Advanced Media) Contracts & Financials Pitch & hit mechanics (eBIS, Stadium (SportVision, Trackman) operations) 12/10/2012 Property of Ari Kaplan. Copyright 2012 6
  • 7. Multistructural data sources (internally collected) MiLB Coach Reports Organizational Video Pro-Scouting Reports Amateur Scouting Injury & Medical Reports International Scouting Advance Scouting Reports Reports 12/10/2012 Property of Ari Kaplan. Copyright 2012 7
  • 8. Understand and manage risks 12/10/2012 Property of Ari Kaplan. Copyright 2012 8
  • 9. Analytics for past, present, future  Learn these three points: What has happened? What is happening? What will happen? 12/10/2012 Property of Ari Kaplan. Copyright 2012 9
  • 10. Find actionable patterns in the data Barry Zito’s Fastball release points come down and over a foot 12/10/2012 Property of Ari Kaplan. Copyright 2012 10
  • 11. Find events preceding a business issue Track consistency and deception of release points and velocity as the season progresses. See how injuries, trades, or assignments from the Minors affect mechanics. 12/10/2012 Property of Ari Kaplan. Copyright 2012 11
  • 12. Predict what might happen from time-series information 12/10/2012 Property of Ari Kaplan. Copyright 2012 12
  • 13. Refocus workers from the mundane to the strategic What happened? What is happening? What will happen?  Scoutable™ reports: based on full coverage of every pitch, every game. The reports are presented in the same formats that many scouts and organizations use today.  Habits: threw FB whenever there was a 3-ball count. Never threw consecutive pickoff moves.  Strengths: changeup had a big fading action. Kept first-pitches down 48% of the time (25% was avg). Plus control of his FB.  Summary: Threw FB 91-94 (34% of all pitches), cutter 88-91 (12%), sinker 91-94 (28%), curveball 75-78 (13%), changeup 85-87 (13%)  Last game compared to before: threw sinkers 16% less often and cutters 14% more often 12/10/2012 Property of Ari Kaplan. Copyright 2012 13
  • 14. Find the “signal from the noise” Example: is a player’s hurt knee affecting their swing? Before injury: white After injury circles are hits, green are misses 12/10/2012 Property of Ari Kaplan. Copyright 2012 14
  • 15. Use intelligence to find opportunities • Where did a pitcher generate outs? What pitch types and locations? Below shows FB up and slider low/away. • Where did he allow hits? FB inner half, BB up in zone outer half. • These reports can be for pitcher/batter matchups, across years, and much more 12/10/2012 Property of Ari Kaplan. Copyright 2012 15
  • 16. The “Human Element”: Quantifying the subjective Which umpires made the most What was Hunter Wendelstedt’s strike zone? frequent bad calls? Umpire Strike Zones 12/10/2012 Property of Ari Kaplan. Copyright 2012 16
  • 17. Use intelligence to better “defend” yourself 12/10/2012 Property of Ari Kaplan. Copyright 2012 17
  • 18. Competition: put yourself in their shoes 12/10/2012 Property of Ari Kaplan. Copyright 2012 18
  • 19. 12/10/2012 Property of Ari Kaplan. Copyright 2012 19
  • 20. The future of batter analysis  Contact point  Elevation angle  Speed off bat  Field direction Image source: Sportvision 12/10/2012 Property of Ari Kaplan. Copyright 2012 20
  • 21. The future of batter analysis Image source: Sportvision 12/10/2012 Property of Ari Kaplan. Copyright 2012 21
  • 22. The future of fielding analysis Image source: Sportvision 12/10/2012 Property of Ari Kaplan. Copyright 2012 22
  • 23. The future of fielding analysis The pivot  6-4-3 Double plays Play # Time from SS to 2B* Pivot time** 1 .60 .60 2 .40 .40 3 .27 .60 4 .53 .40 5 .53 .40 6 .53 .53 7 .67 .33 Image source: Sportvision * From SS releasing the ball to 2B getting the ball ** From 2B getting the ball to 2B releasing the ball 12/10/2012 Property of Ari Kaplan. Copyright 2012 23
  • 24. Create the ULTIMATE game-plan Image source: Sportvision 12/10/2012 Property of Ari Kaplan. Copyright 2012 24