Forecasting the Winner of a Tennis Match - PowerPoint PPT Presentation

Loading...

PPT – Forecasting the Winner of a Tennis Match PowerPoint presentation | free to download - id: 28462-MGJlO



Loading


The Adobe Flash plugin is needed to view this content

Get the plugin now

View by Category
About This Presentation
Title:

Forecasting the Winner of a Tennis Match

Description:

Forecasting the Winner. of a Tennis Match. Franc Klaassen ... Forecasting in practice: Serena-Venus Williams at Wimbledon 2003 ... Prob{Serena wins match} = 70 ... – PowerPoint PPT presentation

Number of Views:446
Avg rating:3.0/5.0
Slides: 24
Provided by: Klaa
Learn more at: http://www1.fee.uva.nl
Category:

less

Write a Comment
User Comments (0)
Transcript and Presenter's Notes

Title: Forecasting the Winner of a Tennis Match


1
Forecasting the Winnerof a Tennis Match
  • Franc Klaassen
  • University of Amsterdam (NL)
  • Jan R. Magnus
  • Tilburg University (NL)
  • TST Congress, London
  • July 29, 2003

2
Overview
  • Forecasting one aspect of a larger tennis
    project
  • Motivation for forecasting
  • How to compute forecasts during a match?
  • Forecasting in practice graph of the 2003
    Ladies Singles Wimbledon final
  • Robustness of the graph
  • Conclusion.

3
Tennis project
  • Testing hypotheses (six papers)
  • 7th game is the most important game in a set
    false
  • Real champions win the big points true.
  • Service strategy (in progress)
  • How to choose the strengths of 1st and 2nd
    services to maximize the probability of winning a
    point?
  • Rule changes (one paper)
  • How to reduce the service dominance? Presented at
    TST-1.
  • Forecasting (two papers)
  • Forecasting winner while match is in progress
    TST-2.

4
Motivation for forecasting
  • Forecasting the winner of a tennis match
  • Before a match
  • Using odds from bookmakers
  • Using statistical model, e.g.,
  • Boulier and Stekler (1999)
  • Clarke and Dyte (2000)
  • During a match
  • Using statistical model
  • ? focus of our paper.

5
Why forecasting during match?
  • TV spectators want information on
  • Which player leads at this moment?
  • Who is most likely to win the match?
  • How did the match develop up to now (momentum,
    winning mood)?

6
TV spectators get info on
  • Score gives info on
  • 1 (Leader) Yes
  • 2 (Likely winner) Partially
  • 4-6 for Agassi-Hewitt Hewitt will probably
    win,
  • 4-6 for Agassi-Henman Agassi will still be
    the favorite
  • 3 (Development up to now) Partially
  • 5-5 can result after 4-4 (match in balance),
  • but also after 5-0 (one player is in a winning
    mood)
  • ? Room for improvement regarding 2 and 3.

7
TV spectators also get info on
  • Match/set stats (1st serve in,...) give info on
  • 2 (Likely winner) Not much
  • 3 (Development up to now) Partially
  • Comparison of 2nd set with 1st set statistics
    gives some insight,
  • but each statistic is too aggregate to give a
    clear picture.
  • Note summary stats provide detailed info on
    specific aspects of each player ? useful, but
    beyond scope of our paper.
  • ? Still room for improvement regarding 2 and 3
  • ? Purpose of current paper.

8
Idea
  • Present the probability that a player will win
    match update it as match unfolds (real-time
    forecasting).
  • Example Agassi-Hewitt
  • At start of match Agassi wins with prob. 60
  • At 4-6 Agassi wins with prob. 30
  • At 4-6/0-3 Agassi wins with prob. 20.
  • Use graph to visualize the probs. of all points
    till now.

9
How to compute the forecasts during a match?
  • Suppose match between players A and B.
  • Goal ProbA wins match at each point up to now.
  • This probability depends on 2 inputs (besides
    score)
  • ProbA wins match at start of match
  • ProbA wins point on serveProbB wins point on
    serve.
  • Implementation using our computer program
    TENNISPROB
  • Choose the two inputs before the match and keep
    them constant
  • Type in the score at each point
  • ? TENNISPROB gives ProbA wins match very
    quickly.

10
How to choose the two inputs?
  • ProbA wins match at start of match
  • We provide an estimate based on rankings (e.g.,
    80),
  • but one can easily improve/overrule that estimate
    if one has specific other info (injury problems,
    specific ability of surface,...) (e.g., 70)
  • ? In the end there is one starting point of the
    graph (70).
  • ProbA wins point on serveProbB wins point on
    serve
  • We provide an estimate based on rankings (e.g.,
    120 both players win 60 of their points on
    service)
  • No need for adjustment the graph hardly depends
    on our choice
  • ? There is an estimate (120).

11
Forecasting in practice Serena-Venus Williams at
Wimbledon 2003
  • Before the match starts, we choose inputs
  • ProbSerena wins match 70
  • ProbSerena wins point on serve
    ProbVenus wins point on serve 116.
  • Then the match starts and graph builds up
  • Note match has not yet been completed
  • ? graph does not use info on later points!

12
set 1
13
set 1
14
set 1
set 2
15
set 1
set 2
set 3
16
set 1
set 2
set 3
17
set 1
set 2
set 3
18
Robustness of the graph
  • Our choices for the two input probabilities may
    be not perfectly correct is that a problem?
  • ? Does profile change a lot if one chooses
  • Starting probability 60 or 80 instead of 70?
  • ProbSerena wins point on serveProbVenus wins
    point on serve 110 or 120 instead of 116?

19
set 1
set 2
set 3
20
set 1
set 2
set 3
21
Conclusion
  • We have introduced a robust method to
  • forecast winner of match as match unfolds
  • New existing papers focus on forecasting at
    start of match, while we do it also for matches
    in progress
  • Info on who will win match and on development of
    match till now
  • Single line makes the information visible at a
    glance
  • Graph can be generated instantly
  • and for any match (not just at Wimbledon)
  • ? Graph is useful in addition to score summary
    statistics.
  • Potential application
  • present graph during change of ends ? TV
    commentator can discuss match developments so far
    (turning points,..)

22
Future research
  • So far two input probs. are kept fixed during
    match updating may improve graph, but
    value-added is unclear.
  • Other aspects of tennis project
  • Service strategy
  • Development of tennis over time
  • Has return indeed improved?
  • In what respects has the womens game changed?
  • Differences between Wimbledon and other
    tournaments
  • Impact of surfaces grass, clay, hard court
  • ? Need more data on grand slam/ATP/WTA
    tournaments.

23
Probability S. Williams wins match
1.0
0.8
0.6
0.4
0.2
set 1
set 2
set 3
0.0
0
20
40
60
80
100
120
140
160
180
Point number
About PowerShow.com