SlideShare a Scribd company logo
2015 OptaPro Analytics Forum
Framework for a Player
Career Forecast Model
Between Multiple Leagues
Howard Hamilton
Founder, Soccermetrics Research
2015 OptaPro Analytics Forum
Developed a career statistical forecasting modelling framework for football players,
automated by applying machine-learning techniques.
Inputs
1. Season statistical performance
2. Physical / playing
characteristics
Outputs
1. Identify peer group of players with comparable
performance
2. Forecast future statistical performance over a limited
horizon
3. Translate performance in one domestic league
competition to performance in another
Expected Interest
 Clubs
 Media
 Betting
 Fantasy
Early Stage: Framework > Results
Main Points
2015 OptaPro Analytics Forum
Baseball
1. Similarity Scores (Bill James, 1980s)
2. Vladimir Forecasting System (Gary Huckabay, 1990s)
3. PECOTA (Nate Silver/Baseball Prospectus, 2003)
PECOTA-inspired forecasting models in other sports
1. SCHOENE (Kevin Pelton/Basketball Prospectus/ESPN, mid 2000s)
2. KUBIAK (Aaron Schatz/Football Outsiders, mid 2000s)
3. VUKOTA (Puck Prospectus, 2010)
Individual / team projection models in football
1. Aaron Nielsen (ENB Sports)
•
One-year projection of individual/team performance
2. Pérez Sánchez et al (2013)
•
Estimating goal-scoring performance in Spanish league
Forecasting Statistical Performance in Sport
Prior Art
2015 OptaPro Analytics Forum
Data scarcity
•
Range of seasons
•
Statistical categories collected
•
League variations
Characteristics of domestic leagues
•
Differences in aging curves between leagues
•
Would a 'universal' aging curve work? Not sure...
•
Statistical translations between leagues
•
Some leagues are very connected, others less so
Challenges
2015 OptaPro Analytics Forum
Data Source: ENB Soccer Database
•
60,000+ players,
•
75 domestic league competitions,
•
500+ clubs
Individual season statistics
•
1992-93 to 2011-12 (European)
•
1992 to 2012 (American/Scandinavian/Japanese)
Database Analysis
All players
•
Season
•
Team
•
Competition
•
Appearances
•
Subs
•
Minutes
•
Yellows / reds
Field players
•
Goals
•
Assists
•
Shots
•
Fouls
Goalkeepers
•
Goals allowed
•
Clean sheets
•
Shots faced
•
Wins
•
Draws
•
Losses
Modeling Components
2015 OptaPro Analytics Forum
Normalize statistical categories
Convert statistical values of players in same competition and season
•
to “standard score”
•
Places statistical performances on one standard distribution
•
This is what allows us to compare players
Identify K comparable players (“nearest neighbors”)
•
Consider players of same age and position
•
Calculate similarity score between statistical records
•
Comparable players: Score about 0.90 - 0.95
•
Relax threshold for “unique” players
Forecast future performance with historical
performance of comparable players
Using regression techniques
• Adjust for aging and regression to mean
• Convert to statistics for league competition of interest
(x-)/
K-NN

Model Description
2015 OptaPro Analytics Forum
Player League Season Similarity
Osvaldo Val Baiano Brazil Serie B 2007 0.961
Wayne Rooney English Premier League 2011-2012 0.957
Oscar Cardozo Portugal Primeira Liga 2009-2010 0.954
Maciej Zurawski Poland Ekstraklasa 2002-2003 0.939
Carlos Tevez English Premier League 2010-2011 0.926
Javi Moreno Spanish Primera 2000-2001 0.925
Katlego Mphela South Africa PSL 2010-2011 0.913
Matt Tubbs England Conference 2010-2011 0.913
Kris Boyd Scotland Premier League 2009-2010 0.905
Goncalves Jonas Brazil Serie A 2010 0.904
Rickie Lambert England League One 2008-2009 0.901
Mario Bermejo Spanish Segunda 2004-2005 0.897
Alan Shearer English Premier League 1996-1997 0.877
Kevin Phillips English Premier League 1999-2000 0.863
Photo by Simon Harriyott
Cristiano Ronaldo: Forward, aged 27 (Spanish Primera 2011/12)
Active Player.
Scored 46 goals in 2011/12
La Liga season.
Nearest Neighbor Results
Nearest Neighbor groups leading goalscorers at Ronaldo's age
0.96 similarity metric – few players had a season as dominant
2015 OptaPro Analytics Forum
Marvin Bejarano: Defender, aged 21 (Bolivia Liga Profesional 2008)
Player League Season Similarity
Fernando Tobio Argentina Primera 2009-2010 0.996
Charlie Wassmer England League Two 2011-2012 0.990
Oswaldo Alanis Mexico Primera 2009-2010 0.985
Jan Vertonghen Netherlands Eredivisie 2007-2008 0.984
Paul Papp Romania Liga I 2009-2010 0.957
Santiago Vergini Paraguay Primera 2009 0.957
Mauricio Casierra Colombia Primera 2006 0.957
Rafael Delgado Argentina Nacional B 2010-2011 0.955
Konstantin Engel Germany 2 Bundesliga 2008-2009 0.954
Jae Sung Lee South Korea K-League 2009 0.953
Koybasi Ismail Turkey Super Lig 2009-2010 0.953
Luke O'Brien England League Two 2008-2009 0.951
Hector Quinones Colombia Primera 2012 0.950
Mate Ghvinianidze Germany 2 Bundesliga 2006-2007 0.950
Franz Schiemer Austria 1 Bundesliga 2006-2007 0.947
Active Player.
Has played for one club
over his career.
5 caps for Bolivia.
0.996 similarity metric – very comparable, but limited defensive data
Nearest Neighbor Results
2015 OptaPro Analytics Forum
Iker Casillas: Goalkeeper, aged 26 (Spanish Primera, 2006-2007)
Active Player.
Has played for one club
over his career.
450+ appearances at
Real Madrid,
160 caps for Spain.
Interesting that Gianluigi Buffon is closest comparable at 26 y/o
Nearest Neighbor Results
Player League Season Similarity
Gianluigi Buffon Italy Serie A 2003-2004 0.994
Mark Crossley English Premier League 1994-1995 0.992
Dionissis Chiotis Greece Super League 2002-2003 0.990
Steve Mandanda France Ligue 1 2010-2011 0.989
Marco Wolfli Switzerland Super League 2007-2008 0.989
Shay Given English Premier League 2001-2002 0.986
Guillermo Ochoa Mexico Primera 2010-2011 0.986
Eduardo Martini Brazil Serie A 2004 0.985
Morgan de Sanctis Italy Serie A 2002-2003 0.984
Hiroki Iikura Japan J1-League 2011 0.982
Cesar Lainez Spanish Segunda 2002-2003 0.981
Marcelo Grohe Brazil Serie A 2012 0.981
Hitoshi Sogahata Japan J1-League 2005 0.980
Henri Sillanpaa Finland Veikkausliiga 2004 0.980
2015 OptaPro Analytics Forum
Projecting career performance is difficult
•
Next steps:
●
Use nearest neighbors to forecast future performance
●
Quantify adjustments for age, league quality, position
●
Create multiple career forecast paths with probabilities
•
Limited horizons important (2-3 years)
•
Probabilistic projections sensible, not necessarily useful
•
Accuracy vs. clarity
•
Diverse range of statistical categories necessary –
•
Attacking and defending contributions and impact
•
Advanced metrics
Data normalization is a necessity!
Club projections are logical step
Need to enforce a “conservation of goals” in the universe of data in our
system, i.e:
Total goals scored == total goals conceded
Photo by Simon Harriyott
Conclusions
2015 OptaPro Analytics Forum
Customization
•
Integrate with financial/medical databases, scouting data
•
Greatest utility at football operations/sporting director level
Biggest challenge: Data!
Not just data on all players in league, but players
•
in all other leagues of interest
•
Some statistical categories not available in some leagues
• As always, data collection and analysis problems are non-trivial
Photo by JD Hancock
Knowledge Transfer
2015 OptaPro Analytics Forum
Thank You!
Special Thanks To:
OptaPro (Invitation to Forum)
Aaron Nielsen (ENB Database access)
Simon Harriyott (Presentation at Forum)
For more information contact
Soccermetrics Research
info@soccermetrics.net
www.soccermetrics.net
@soccermetrics

More Related Content

Viewers also liked

Sport Marketing Chapter 1
Sport Marketing Chapter 1Sport Marketing Chapter 1
Sport Marketing Chapter 1
teparlett
 
Improve passing-and-receiving
Improve passing-and-receivingImprove passing-and-receiving
Improve passing-and-receiving
Ricardo Luiz Pace
 
Rekha dey sports and learning
Rekha dey sports and learningRekha dey sports and learning
Rekha dey sports and learning
pratyush227
 
P.e powerpoint
P.e powerpointP.e powerpoint
P.e powerpoint
usef1234
 

Viewers also liked (16)

Sport Marketing Chapter 1
Sport Marketing Chapter 1Sport Marketing Chapter 1
Sport Marketing Chapter 1
 
WS II Ch 5
WS II Ch 5WS II Ch 5
WS II Ch 5
 
Survey on cultural change and sport
Survey on cultural change and sportSurvey on cultural change and sport
Survey on cultural change and sport
 
Barcelona philosophy
Barcelona philosophyBarcelona philosophy
Barcelona philosophy
 
10 grassroots soccer trends for the next 10 years
10 grassroots soccer trends for the next 10 years10 grassroots soccer trends for the next 10 years
10 grassroots soccer trends for the next 10 years
 
Learning from the past – How industry repeats persuasive tactics to promote s...
Learning from the past – How industry repeats persuasive tactics to promote s...Learning from the past – How industry repeats persuasive tactics to promote s...
Learning from the past – How industry repeats persuasive tactics to promote s...
 
INNOVACIÓN EN LA INDUSTRIA DEL DEPORTE SEPTIEMBRE 2014
INNOVACIÓN EN LA INDUSTRIA DEL DEPORTE SEPTIEMBRE 2014INNOVACIÓN EN LA INDUSTRIA DEL DEPORTE SEPTIEMBRE 2014
INNOVACIÓN EN LA INDUSTRIA DEL DEPORTE SEPTIEMBRE 2014
 
The 'Future of Sport' through a digital lens
The 'Future of Sport' through a digital lensThe 'Future of Sport' through a digital lens
The 'Future of Sport' through a digital lens
 
Industrialization of Sports
Industrialization of SportsIndustrialization of Sports
Industrialization of Sports
 
Improve passing-and-receiving
Improve passing-and-receivingImprove passing-and-receiving
Improve passing-and-receiving
 
GRUPETTO urban bike transmedia proyect 1.0
GRUPETTO urban bike transmedia proyect 1.0 GRUPETTO urban bike transmedia proyect 1.0
GRUPETTO urban bike transmedia proyect 1.0
 
Servicios federaciones grupo campus marzo 2016
Servicios federaciones grupo campus marzo 2016Servicios federaciones grupo campus marzo 2016
Servicios federaciones grupo campus marzo 2016
 
When will Virtual Reality become Reality? @NED2015
When will Virtual Reality become Reality? @NED2015When will Virtual Reality become Reality? @NED2015
When will Virtual Reality become Reality? @NED2015
 
Rekha dey sports and learning
Rekha dey sports and learningRekha dey sports and learning
Rekha dey sports and learning
 
Trends In Garment Decoration
Trends In Garment DecorationTrends In Garment Decoration
Trends In Garment Decoration
 
P.e powerpoint
P.e powerpointP.e powerpoint
P.e powerpoint
 

Similar to Framework for Forecasting Professional Soccer Player Career Paths

Top 20 Under 21 Football Value Index by Prime Time Sport for Soccerex
Top 20 Under 21 Football Value Index by Prime Time Sport for SoccerexTop 20 Under 21 Football Value Index by Prime Time Sport for Soccerex
Top 20 Under 21 Football Value Index by Prime Time Sport for Soccerex
Prime Time Sport
 
Football Game prediction
Football Game predictionFootball Game prediction
Football Game prediction
lulyon
 
Football Game prediction
Football Game predictionFootball Game prediction
Football Game prediction
lulyon
 
stats-llc-prozone-team-european-090000439.html
stats-llc-prozone-team-european-090000439.htmlstats-llc-prozone-team-european-090000439.html
stats-llc-prozone-team-european-090000439.html
Federico Winer
 
Major League Soccer Player Analysis
Major League Soccer Player AnalysisMajor League Soccer Player Analysis
Major League Soccer Player Analysis
Chris Armstrong
 
Sports Analytics: Market Shares, Strategy, and Forecasts, Worldwide, 2015 to ...
Sports Analytics: Market Shares, Strategy, and Forecasts, Worldwide, 2015 to ...Sports Analytics: Market Shares, Strategy, and Forecasts, Worldwide, 2015 to ...
Sports Analytics: Market Shares, Strategy, and Forecasts, Worldwide, 2015 to ...
Shrikant Mandlik
 

Similar to Framework for Forecasting Professional Soccer Player Career Paths (20)

Sexiest of the Sexiest Job Profile: Sports Analyst
Sexiest of the Sexiest Job Profile: Sports AnalystSexiest of the Sexiest Job Profile: Sports Analyst
Sexiest of the Sexiest Job Profile: Sports Analyst
 
Alex Kornilov: Building Big Data Company in Sports-Betting Industry - BETEGY ...
Alex Kornilov: Building Big Data Company in Sports-Betting Industry - BETEGY ...Alex Kornilov: Building Big Data Company in Sports-Betting Industry - BETEGY ...
Alex Kornilov: Building Big Data Company in Sports-Betting Industry - BETEGY ...
 
Top 20 Under 21 Football Value Index by Prime Time Sport for Soccerex
Top 20 Under 21 Football Value Index by Prime Time Sport for SoccerexTop 20 Under 21 Football Value Index by Prime Time Sport for Soccerex
Top 20 Under 21 Football Value Index by Prime Time Sport for Soccerex
 
Football Game prediction
Football Game predictionFootball Game prediction
Football Game prediction
 
Football Game prediction
Football Game predictionFootball Game prediction
Football Game prediction
 
MYagonism basketball analytics innovation -public-
MYagonism basketball analytics innovation -public-MYagonism basketball analytics innovation -public-
MYagonism basketball analytics innovation -public-
 
The Essential Role of Data Feeds in Modern Football
The Essential Role of Data Feeds in Modern FootballThe Essential Role of Data Feeds in Modern Football
The Essential Role of Data Feeds in Modern Football
 
The Football Analytics Handbook
The Football Analytics HandbookThe Football Analytics Handbook
The Football Analytics Handbook
 
Data warehouse Soccer Project
Data warehouse Soccer Project Data warehouse Soccer Project
Data warehouse Soccer Project
 
Big Data for Big Sports
Big Data for Big SportsBig Data for Big Sports
Big Data for Big Sports
 
Sports Analytics 2015 Brochure
Sports Analytics 2015 BrochureSports Analytics 2015 Brochure
Sports Analytics 2015 Brochure
 
stats-llc-prozone-team-european-090000439.html
stats-llc-prozone-team-european-090000439.htmlstats-llc-prozone-team-european-090000439.html
stats-llc-prozone-team-european-090000439.html
 
Discovering The Best Free Football Scouting Software
Discovering The Best Free Football Scouting SoftwareDiscovering The Best Free Football Scouting Software
Discovering The Best Free Football Scouting Software
 
Federated Ontology for Sports- Paper
Federated Ontology for Sports- PaperFederated Ontology for Sports- Paper
Federated Ontology for Sports- Paper
 
Major League Soccer Player Analysis
Major League Soccer Player AnalysisMajor League Soccer Player Analysis
Major League Soccer Player Analysis
 
Neque contumelia deck
Neque contumelia deckNeque contumelia deck
Neque contumelia deck
 
Football Result Prediction using Dixon Coles Algorithm
Football Result Prediction using Dixon Coles AlgorithmFootball Result Prediction using Dixon Coles Algorithm
Football Result Prediction using Dixon Coles Algorithm
 
Sports Analytics: Market Shares, Strategy, and Forecasts, Worldwide, 2015 to ...
Sports Analytics: Market Shares, Strategy, and Forecasts, Worldwide, 2015 to ...Sports Analytics: Market Shares, Strategy, and Forecasts, Worldwide, 2015 to ...
Sports Analytics: Market Shares, Strategy, and Forecasts, Worldwide, 2015 to ...
 
German wins world cup with big data
German wins world cup with big dataGerman wins world cup with big data
German wins world cup with big data
 
Big Data BizViz Sports Analytics
Big Data BizViz Sports AnalyticsBig Data BizViz Sports Analytics
Big Data BizViz Sports Analytics
 

More from Soccermetrics Research LLC

More from Soccermetrics Research LLC (8)

MLS X.0: Identifying Major League Soccer generations
MLS X.0: Identifying Major League Soccer generationsMLS X.0: Identifying Major League Soccer generations
MLS X.0: Identifying Major League Soccer generations
 
Major League Soccer 2017 Front Office Efficiency
Major League Soccer 2017 Front Office EfficiencyMajor League Soccer 2017 Front Office Efficiency
Major League Soccer 2017 Front Office Efficiency
 
Bayesian Analysis of Draft Pick Value in Major League Soccer
Bayesian Analysis of Draft Pick Value in Major League SoccerBayesian Analysis of Draft Pick Value in Major League Soccer
Bayesian Analysis of Draft Pick Value in Major League Soccer
 
Major League Soccer 2016 Front Office Efficiency
Major League Soccer 2016 Front Office EfficiencyMajor League Soccer 2016 Front Office Efficiency
Major League Soccer 2016 Front Office Efficiency
 
Precision Guesswork: History of MLS Draft Value (CASSIS 2016)
Precision Guesswork: History of MLS Draft Value (CASSIS 2016)Precision Guesswork: History of MLS Draft Value (CASSIS 2016)
Precision Guesswork: History of MLS Draft Value (CASSIS 2016)
 
Major League Soccer 2015 Front Office Efficiency
Major League Soccer 2015 Front Office EfficiencyMajor League Soccer 2015 Front Office Efficiency
Major League Soccer 2015 Front Office Efficiency
 
MLS Front-Office Efficiency: A Club-by-Club History
MLS Front-Office Efficiency: A Club-by-Club HistoryMLS Front-Office Efficiency: A Club-by-Club History
MLS Front-Office Efficiency: A Club-by-Club History
 
MLS Front-Office Efficiency Ratings 2014
MLS Front-Office Efficiency Ratings 2014MLS Front-Office Efficiency Ratings 2014
MLS Front-Office Efficiency Ratings 2014
 

Recently uploaded

Recently uploaded (20)

Tiger Exchange ID: Get Sports Betting & Cricket ID at Tiger Exchange
Tiger Exchange ID:  Get Sports Betting & Cricket ID at Tiger ExchangeTiger Exchange ID:  Get Sports Betting & Cricket ID at Tiger Exchange
Tiger Exchange ID: Get Sports Betting & Cricket ID at Tiger Exchange
 
Unveiling the Transformative Legacy of Cricplus
Unveiling the Transformative Legacy of CricplusUnveiling the Transformative Legacy of Cricplus
Unveiling the Transformative Legacy of Cricplus
 
Germany Vs Scotland UEFA EURO 2024 trophy tour makes final four stops as Germ...
Germany Vs Scotland UEFA EURO 2024 trophy tour makes final four stops as Germ...Germany Vs Scotland UEFA EURO 2024 trophy tour makes final four stops as Germ...
Germany Vs Scotland UEFA EURO 2024 trophy tour makes final four stops as Germ...
 
Online Sports Betting In India online betting
Online Sports Betting In India  online bettingOnline Sports Betting In India  online betting
Online Sports Betting In India online betting
 
Slovakia Vs Romania Slovakia odds to win Euro 2024 Prediction, Outright Odds,...
Slovakia Vs Romania Slovakia odds to win Euro 2024 Prediction, Outright Odds,...Slovakia Vs Romania Slovakia odds to win Euro 2024 Prediction, Outright Odds,...
Slovakia Vs Romania Slovakia odds to win Euro 2024 Prediction, Outright Odds,...
 
Winbuzz login: Get Instant Winbuzz Login Id, and Cricket Id on Winbuzz
Winbuzz login: Get Instant Winbuzz Login Id, and Cricket Id on WinbuzzWinbuzz login: Get Instant Winbuzz Login Id, and Cricket Id on Winbuzz
Winbuzz login: Get Instant Winbuzz Login Id, and Cricket Id on Winbuzz
 
Albania Vs Spain Albania Euro 2024 squad Who is Sylvinho bringing to the Euro...
Albania Vs Spain Albania Euro 2024 squad Who is Sylvinho bringing to the Euro...Albania Vs Spain Albania Euro 2024 squad Who is Sylvinho bringing to the Euro...
Albania Vs Spain Albania Euro 2024 squad Who is Sylvinho bringing to the Euro...
 
Albania vs Spain Euro Cup 2024 Very Close Armando Broja Optimistic Albania Wi...
Albania vs Spain Euro Cup 2024 Very Close Armando Broja Optimistic Albania Wi...Albania vs Spain Euro Cup 2024 Very Close Armando Broja Optimistic Albania Wi...
Albania vs Spain Euro Cup 2024 Very Close Armando Broja Optimistic Albania Wi...
 
Belgium Vs Slovakia Courtois Ruled Out of Euro 2024.docx
Belgium Vs Slovakia Courtois Ruled Out of Euro 2024.docxBelgium Vs Slovakia Courtois Ruled Out of Euro 2024.docx
Belgium Vs Slovakia Courtois Ruled Out of Euro 2024.docx
 
Serbia vs England Tickets: Serbia's UEFA Euro 2024 Squad, A New Era of Redemp...
Serbia vs England Tickets: Serbia's UEFA Euro 2024 Squad, A New Era of Redemp...Serbia vs England Tickets: Serbia's UEFA Euro 2024 Squad, A New Era of Redemp...
Serbia vs England Tickets: Serbia's UEFA Euro 2024 Squad, A New Era of Redemp...
 
Croatia Vs Italy Croatia's Euro 2024 Journey can Modric and Team Survive the ...
Croatia Vs Italy Croatia's Euro 2024 Journey can Modric and Team Survive the ...Croatia Vs Italy Croatia's Euro 2024 Journey can Modric and Team Survive the ...
Croatia Vs Italy Croatia's Euro 2024 Journey can Modric and Team Survive the ...
 
Spain Vs Croatia Euro Cup 2024 Spain announces provisional squad, Morata, Yam...
Spain Vs Croatia Euro Cup 2024 Spain announces provisional squad, Morata, Yam...Spain Vs Croatia Euro Cup 2024 Spain announces provisional squad, Morata, Yam...
Spain Vs Croatia Euro Cup 2024 Spain announces provisional squad, Morata, Yam...
 
Turkey Vs Portugal-UEFA EURO 2024 Montella calls up three Serie A players to ...
Turkey Vs Portugal-UEFA EURO 2024 Montella calls up three Serie A players to ...Turkey Vs Portugal-UEFA EURO 2024 Montella calls up three Serie A players to ...
Turkey Vs Portugal-UEFA EURO 2024 Montella calls up three Serie A players to ...
 
Akshay Ram on Adobe's Creative Strategy and Execution, the Present and Future...
Akshay Ram on Adobe's Creative Strategy and Execution, the Present and Future...Akshay Ram on Adobe's Creative Strategy and Execution, the Present and Future...
Akshay Ram on Adobe's Creative Strategy and Execution, the Present and Future...
 
Eight Barcelona Stars in Spain's Euro 2024 Pre-List.docx
Eight Barcelona Stars in Spain's Euro 2024 Pre-List.docxEight Barcelona Stars in Spain's Euro 2024 Pre-List.docx
Eight Barcelona Stars in Spain's Euro 2024 Pre-List.docx
 
Denmark vs Serbia Tickets: Denmark's Inspirational Journey to the Euro Cup 2024
Denmark vs Serbia Tickets: Denmark's Inspirational Journey to the Euro Cup 2024Denmark vs Serbia Tickets: Denmark's Inspirational Journey to the Euro Cup 2024
Denmark vs Serbia Tickets: Denmark's Inspirational Journey to the Euro Cup 2024
 
JORNADA 8 LIGA MURO 2024BALONCESTO12.pdf
JORNADA 8 LIGA MURO 2024BALONCESTO12.pdfJORNADA 8 LIGA MURO 2024BALONCESTO12.pdf
JORNADA 8 LIGA MURO 2024BALONCESTO12.pdf
 
The Richest Female Athletes of 2024: Champions of Wealth and Excellence | CIO...
The Richest Female Athletes of 2024: Champions of Wealth and Excellence | CIO...The Richest Female Athletes of 2024: Champions of Wealth and Excellence | CIO...
The Richest Female Athletes of 2024: Champions of Wealth and Excellence | CIO...
 
TAM Sports-IPL 17 Advertising Report- M01 - M71.xlsx - IPL 17 FCT (Commercial...
TAM Sports-IPL 17 Advertising Report- M01 - M71.xlsx - IPL 17 FCT (Commercial...TAM Sports-IPL 17 Advertising Report- M01 - M71.xlsx - IPL 17 FCT (Commercial...
TAM Sports-IPL 17 Advertising Report- M01 - M71.xlsx - IPL 17 FCT (Commercial...
 
Croatia and Italy Set for Challenging UEFA Euro 2024 Campaigns.docx
Croatia and Italy Set for Challenging UEFA Euro 2024 Campaigns.docxCroatia and Italy Set for Challenging UEFA Euro 2024 Campaigns.docx
Croatia and Italy Set for Challenging UEFA Euro 2024 Campaigns.docx
 

Framework for Forecasting Professional Soccer Player Career Paths

  • 1. 2015 OptaPro Analytics Forum Framework for a Player Career Forecast Model Between Multiple Leagues Howard Hamilton Founder, Soccermetrics Research
  • 2. 2015 OptaPro Analytics Forum Developed a career statistical forecasting modelling framework for football players, automated by applying machine-learning techniques. Inputs 1. Season statistical performance 2. Physical / playing characteristics Outputs 1. Identify peer group of players with comparable performance 2. Forecast future statistical performance over a limited horizon 3. Translate performance in one domestic league competition to performance in another Expected Interest  Clubs  Media  Betting  Fantasy Early Stage: Framework > Results Main Points
  • 3. 2015 OptaPro Analytics Forum Baseball 1. Similarity Scores (Bill James, 1980s) 2. Vladimir Forecasting System (Gary Huckabay, 1990s) 3. PECOTA (Nate Silver/Baseball Prospectus, 2003) PECOTA-inspired forecasting models in other sports 1. SCHOENE (Kevin Pelton/Basketball Prospectus/ESPN, mid 2000s) 2. KUBIAK (Aaron Schatz/Football Outsiders, mid 2000s) 3. VUKOTA (Puck Prospectus, 2010) Individual / team projection models in football 1. Aaron Nielsen (ENB Sports) • One-year projection of individual/team performance 2. Pérez Sánchez et al (2013) • Estimating goal-scoring performance in Spanish league Forecasting Statistical Performance in Sport Prior Art
  • 4. 2015 OptaPro Analytics Forum Data scarcity • Range of seasons • Statistical categories collected • League variations Characteristics of domestic leagues • Differences in aging curves between leagues • Would a 'universal' aging curve work? Not sure... • Statistical translations between leagues • Some leagues are very connected, others less so Challenges
  • 5. 2015 OptaPro Analytics Forum Data Source: ENB Soccer Database • 60,000+ players, • 75 domestic league competitions, • 500+ clubs Individual season statistics • 1992-93 to 2011-12 (European) • 1992 to 2012 (American/Scandinavian/Japanese) Database Analysis All players • Season • Team • Competition • Appearances • Subs • Minutes • Yellows / reds Field players • Goals • Assists • Shots • Fouls Goalkeepers • Goals allowed • Clean sheets • Shots faced • Wins • Draws • Losses Modeling Components
  • 6. 2015 OptaPro Analytics Forum Normalize statistical categories Convert statistical values of players in same competition and season • to “standard score” • Places statistical performances on one standard distribution • This is what allows us to compare players Identify K comparable players (“nearest neighbors”) • Consider players of same age and position • Calculate similarity score between statistical records • Comparable players: Score about 0.90 - 0.95 • Relax threshold for “unique” players Forecast future performance with historical performance of comparable players Using regression techniques • Adjust for aging and regression to mean • Convert to statistics for league competition of interest (x-)/ K-NN  Model Description
  • 7. 2015 OptaPro Analytics Forum Player League Season Similarity Osvaldo Val Baiano Brazil Serie B 2007 0.961 Wayne Rooney English Premier League 2011-2012 0.957 Oscar Cardozo Portugal Primeira Liga 2009-2010 0.954 Maciej Zurawski Poland Ekstraklasa 2002-2003 0.939 Carlos Tevez English Premier League 2010-2011 0.926 Javi Moreno Spanish Primera 2000-2001 0.925 Katlego Mphela South Africa PSL 2010-2011 0.913 Matt Tubbs England Conference 2010-2011 0.913 Kris Boyd Scotland Premier League 2009-2010 0.905 Goncalves Jonas Brazil Serie A 2010 0.904 Rickie Lambert England League One 2008-2009 0.901 Mario Bermejo Spanish Segunda 2004-2005 0.897 Alan Shearer English Premier League 1996-1997 0.877 Kevin Phillips English Premier League 1999-2000 0.863 Photo by Simon Harriyott Cristiano Ronaldo: Forward, aged 27 (Spanish Primera 2011/12) Active Player. Scored 46 goals in 2011/12 La Liga season. Nearest Neighbor Results Nearest Neighbor groups leading goalscorers at Ronaldo's age 0.96 similarity metric – few players had a season as dominant
  • 8. 2015 OptaPro Analytics Forum Marvin Bejarano: Defender, aged 21 (Bolivia Liga Profesional 2008) Player League Season Similarity Fernando Tobio Argentina Primera 2009-2010 0.996 Charlie Wassmer England League Two 2011-2012 0.990 Oswaldo Alanis Mexico Primera 2009-2010 0.985 Jan Vertonghen Netherlands Eredivisie 2007-2008 0.984 Paul Papp Romania Liga I 2009-2010 0.957 Santiago Vergini Paraguay Primera 2009 0.957 Mauricio Casierra Colombia Primera 2006 0.957 Rafael Delgado Argentina Nacional B 2010-2011 0.955 Konstantin Engel Germany 2 Bundesliga 2008-2009 0.954 Jae Sung Lee South Korea K-League 2009 0.953 Koybasi Ismail Turkey Super Lig 2009-2010 0.953 Luke O'Brien England League Two 2008-2009 0.951 Hector Quinones Colombia Primera 2012 0.950 Mate Ghvinianidze Germany 2 Bundesliga 2006-2007 0.950 Franz Schiemer Austria 1 Bundesliga 2006-2007 0.947 Active Player. Has played for one club over his career. 5 caps for Bolivia. 0.996 similarity metric – very comparable, but limited defensive data Nearest Neighbor Results
  • 9. 2015 OptaPro Analytics Forum Iker Casillas: Goalkeeper, aged 26 (Spanish Primera, 2006-2007) Active Player. Has played for one club over his career. 450+ appearances at Real Madrid, 160 caps for Spain. Interesting that Gianluigi Buffon is closest comparable at 26 y/o Nearest Neighbor Results Player League Season Similarity Gianluigi Buffon Italy Serie A 2003-2004 0.994 Mark Crossley English Premier League 1994-1995 0.992 Dionissis Chiotis Greece Super League 2002-2003 0.990 Steve Mandanda France Ligue 1 2010-2011 0.989 Marco Wolfli Switzerland Super League 2007-2008 0.989 Shay Given English Premier League 2001-2002 0.986 Guillermo Ochoa Mexico Primera 2010-2011 0.986 Eduardo Martini Brazil Serie A 2004 0.985 Morgan de Sanctis Italy Serie A 2002-2003 0.984 Hiroki Iikura Japan J1-League 2011 0.982 Cesar Lainez Spanish Segunda 2002-2003 0.981 Marcelo Grohe Brazil Serie A 2012 0.981 Hitoshi Sogahata Japan J1-League 2005 0.980 Henri Sillanpaa Finland Veikkausliiga 2004 0.980
  • 10. 2015 OptaPro Analytics Forum Projecting career performance is difficult • Next steps: ● Use nearest neighbors to forecast future performance ● Quantify adjustments for age, league quality, position ● Create multiple career forecast paths with probabilities • Limited horizons important (2-3 years) • Probabilistic projections sensible, not necessarily useful • Accuracy vs. clarity • Diverse range of statistical categories necessary – • Attacking and defending contributions and impact • Advanced metrics Data normalization is a necessity! Club projections are logical step Need to enforce a “conservation of goals” in the universe of data in our system, i.e: Total goals scored == total goals conceded Photo by Simon Harriyott Conclusions
  • 11. 2015 OptaPro Analytics Forum Customization • Integrate with financial/medical databases, scouting data • Greatest utility at football operations/sporting director level Biggest challenge: Data! Not just data on all players in league, but players • in all other leagues of interest • Some statistical categories not available in some leagues • As always, data collection and analysis problems are non-trivial Photo by JD Hancock Knowledge Transfer
  • 12. 2015 OptaPro Analytics Forum Thank You! Special Thanks To: OptaPro (Invitation to Forum) Aaron Nielsen (ENB Database access) Simon Harriyott (Presentation at Forum) For more information contact Soccermetrics Research info@soccermetrics.net www.soccermetrics.net @soccermetrics