Dr Adrian Schembri Dr Anthony Bedford Bradley OBree Natalie Bressanutti RMIT Sports Statistics Research Group School of Mathematical and Geospatial Sciences RMIT University Melbourne Australia ID: 143656
Download Presentation The PPT/PDF document "Comparing Market Efficiency with Traditi..." is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.
Slide1
Comparing Market Efficiency with Traditional and Non-Traditional Ratings Systems in ATP Tennis
Dr Adrian Schembri
Dr Anthony Bedford Bradley O’BreeNatalie BressanuttiRMIT Sports Statistics Research GroupSchool of Mathematical andGeospatial SciencesRMIT UniversityMelbourne, Australia
www.rmit.edu.au/sportstatsSlide2
Aims of the Presentation
Structure of ATP tennis, rankings, and tournaments;
Challenges associated with predicting outcomes of tennis matches; Utilising the SPARKS and Elo ratings to predict ATP tennis; Evaluate changes in market efficiency in tennis over the past eight years.RMIT University©2011
RMIT Sports Statistics
2Slide3
Background to ATP Tennis
RMIT University©2011
RMIT Sports Statistics3 ATP: Association of Tennis Professionals; Consists of 65 individual tournaments each year for men playing at the highest level;
Additional:178 tournaments played in the Challenger Tour;
534 tournaments played in Futures tennis.Slide4
ATP Tennis Rankings
RMIT University©2011
RMIT Sports Statistics4 “Used to determine qualification for entry and seeding in all tournaments for both singles and doubles”; The rankings period is always the past 52 weeks prior to the current week.Slide5
ATP Tennis Rankings – Sept 12th, 2011
RMIT University©2011
RMIT Sports Statistics5Slide6
How Predictive are Tennis Rankings? Case Study
RMIT University©2011
RMIT Sports Statistics6Australian Hardcourt Titles January, 1998
Adelaide, Surface – Hardcourt
Lleyton
Hewitt
(AUS)
Andre Agassi (USA)
Age
16 years
27 years
ATP
Ranking
550
86 (6
th
in Jan, 1999)Slide7
How Predictive are Tennis Rankings? Case Study
RMIT University©2011
RMIT Sports Statistics7Robby Ginepri
Robin Soderling
6 - 4
7 - 5
Age
16 years
27 years
Tourn
Seed
Unseeded
1
Aircel
Chennai
Open
January 4 - 10, 2010
Chennai, Surface –
HardcourtSlide8
Challenges Associated with Predicting Outcomes in ATP Tennis
RMIT University©2011
RMIT Sports Statistics8 Individual sport and therefore natural variation due to individual differences prior to and during a match; Constant variations in the quality of different players:
Players climbing the rankings; Players dropping in the rankings; Players ranking remaining stagnant.
The importance of different tournaments varies for each individual players.Slide9
Recent Papers on Predicting ATP Tennis and Evaluating Market Efficiency
RMIT University©2011
RMIT Sports Statistics9 Forrest and McHale (2007) reviewed the potential for long-shot bias in men’s tennis; Klaassen and Magnus (2003) developed a probability-based model to evaluate the likelihood of a player winning a match, whilst Easton and Uylangco (2010) extended this to a point-by-point model;
A range of probability-based models are available online, however these are typically volatile and reactive to events such as breaks in serve and each set result (e.g., www.strategicgames.com.au).Slide10
Aims of the Current Paper
Evaluate the efficiency of various tennis betting markets over the past eight years;
Compare the efficiency of these markets with traditional ratings systems such as Elo and a non-traditional ratings system such as SPARKS; Identify where inefficiencies in the market lie and the degree to which this has varied over time.RMIT University©2011
RMIT Sports Statistics
10Slide11
www.rmit.edu.au/sportstats
Elo Ratings and the SPARKS ModelSlide12
Introduction to Ratings Systems
12
RMIT University©2011
RMIT Sports Statistics
Typically used to:
Monitor the relative ranking of players with other players in the same league;
Identify the probability of each team or player winning their next match.
Have been developed in the context of individual (chess, tennis) or group based sports (e.g., AFL football, NBA);
The initial ratings suggest which player is likely to win, with the difference between their old ratings being used to calculate a new rating after the match is played.Slide13
Introduction to SPARKS
13
RMIT University©2011
RMIT Sports Statistics
Initially developed by Bedford and Clarke (2000) to provide an alternative to traditional ratings systems;
Differ from Elo-type ratings systems as SPARKS considers the margin of the result;
Has been recently utilised to evaluate other characteristics such as the travel effect in tennis (Bedford et al., 2011).Slide14
Introduction to SPARKS
14
RMIT University©2011
RMIT Sports Statistics
where
whereSlide15
Introduction to SPARKS
15
RMIT University©2011
RMIT Sports StatisticsSlide16
SPARKS: Case Study
16
RMIT University©2011
RMIT Sports Statistics
Robin Soderling (SWE)
Ryan Harrison
(USA)
6-2 6-4
Seeding
1
Qualifier
Pre-Match Rating
2986.3
978.4
Expected Outcome
20.1
-20.1
Observed Outcome
Win
Loss
SPARKS
24
6
SPARKS Difference
18
-18
Residuals
-2.1
2.1
Post-Match Rating
2975.9
988.8Slide17
Longitudinal Examination of SPARKS
17
RMIT University©2011
RMIT Sports StatisticsSlide18
Limitations of SPARKS: Case Study
18
RMIT University©2011
RMIT Sports Statistics
Player
Set 1
Set 2
Set 3
Set 4
Calculation
SPARKS (Diff)
Player 1
7
7
7
21 + (3*6)
39 (21)
Player 2
6
6
6
18 + (0*6)
18 (21)
Player
Set 1
Set 2
Set 3
Set 4
Calculation
SPARKS
Player 1
6
3
6
6
21 + (3*6)
39 (21)
Player
2
2
6
2
2
12 + (1*6)
18 (21)
+Slide19
Limitations of SPARKS: Case Study
19
RMIT University©2011
RMIT Sports Statistics
Player
Set 1
Set 2
Set 3
Set 4
Calculation
SPARKS (Diff)
Player 1
7
7
7
21 + (3*6)
39 (21)
Player 2
6
6
6
18 + (0*6)
18 (21)
Player
Set 1
Set 2
Set 3
Set 4
Calculation
SPARKS
Player 1
6
3
6
6
21 + (3*6)
39 (21)
Player
2
2
6
2
2
12 + (1*6)
18 (21)
Player 2 competitive in all three sets.
+Slide20
Limitations of SPARKS: Case Study
20
RMIT University©2011
RMIT Sports Statistics
Player
Set 1
Set 2
Set 3
Set 4
Calculation
SPARKS (Diff)
Player 1
7
7
7
21 + (3*6)
39 (21)
Player 2
6
6
6
18 + (0*6)
18 (21)
Player
Set 1
Set 2
Set 3
Set 4
Calculation
SPARKS
Player 1
6
3
6
6
21 + (3*6)
39 (21)
Player
2
2
6
2
2
12 + (1*6)
18 (21)
Player 2 competitive in all three sets.
Player 2 competitive in 1 out of 4 sets.Slide21
Historical Results of the SPARKS Model
21
RMIT University©2011
RMIT Sports Statistics
Year
Win Prediction in
all
ATP Matches
2003
.64
2004
.64
2005
.69
2006
.67
2007
.66
2008
.67
2009
.69
2010
.72
The following table displays historical results of the raw SPARKS model over the past 8 years.
+Slide22
Historical Results of the SPARKS Model
22
RMIT University©2011
RMIT Sports Statistics
Year
Win Prediction in
all
ATP Matches
2003
.64
2004
.64
2005
.69
2006
.67
2007
.66
2008
.67
2009
.69
2010
.72
The following table displays historical results of the raw SPARKS model over the past 8 years.Slide23
Banding of Probabilities
23
RMIT University©2011
RMIT Sports Statistics
Lower Band
Upper Band
Midpoint
0.00
0.05
0.025
0.05
0.10
0.075
0.10
0.15
0.125
0.15
0.20
0.175
0.20
0.25
0.225
0.25
0.30
0.275
0.30
0.35
0.325
0.35
0.40
0.375
0.40
0.45
0.425
0.45
0.50
0.475
Probability banding is used primarily to determine whether a models predicted probability of a given result is accurate;
Enables an assessment of whether the probability attributed to a given result is appropriate based on reviewing all results within the band;
For example, if 200 matches within a given tennis season are within the .20 to .25 probability band, then between 20% and 25% (or approx 45 matches) of these matches should be won by the players in question.Slide24
Banding and the SPARKS Model
24
RMIT University©2011
RMIT Sports Statistics
Lower Band
Upper Band
Midpoint
0.00
0.05
0.025
0.05
0.10
0.075
0.10
0.15
0.125
0.15
0.20
0.175
0.20
0.25
0.225
0.25
0.30
0.275
0.30
0.35
0.325
0.35
0.40
0.375
0.40
0.45
0.425
0.45
0.50
0.475
Lower Band
Upper Band
Midpoint
0.50
0.55
0.525
0.55
0.60
0.575
0.60
0.65
0.625
0.65
0.70
0.675
0.70
0.75
0.725
0.75
0.80
0.775
0.80
0.85
0.825
0.85
0.90
0.875
0.90
0.95
0.925
0.95
1.00
0.975
+Slide25
Banding and the SPARKS Model
25
RMIT University©2011
RMIT Sports Statistics
Lower Band
Upper Band
Midpoint
0.00
0.05
0.025
0.05
0.10
0.075
0.10
0.15
0.125
0.15
0.20
0.175
0.20
0.25
0.225
0.25
0.30
0.275
0.30
0.35
0.325
0.35
0.40
0.375
0.40
0.45
0.425
0.45
0.50
0.475
Lower Band
Upper Band
Midpoint
0.50
0.55
0.525
0.55
0.60
0.575
0.60
0.65
0.625
0.65
0.70
0.675
0.70
0.75
0.725
0.75
0.80
0.775
0.80
0.85
0.825
0.85
0.90
0.875
0.90
0.95
0.925
0.95
1.00
0.975
Represent the underdog.
Represent the favourite.Slide26
Banding and the SPARKS Model
26
RMIT University©2011
RMIT Sports StatisticsSlide27
Banding and the SPARKS Model (2003-2010)
27
RMIT University©2011
RMIT Sports Statistics
+Slide28
Banding and the SPARKS Model (2003-2010)
28
RMIT University©2011
RMIT Sports Statistics
Under-estimates the probability of the under-dog winning.
Over-estimates the probability of the favorite winning.Slide29
www.rmit.edu.au/sportstats
Elo RatingsSlide30
Introduction to Elo Ratings
30
RMIT University©2011
RMIT Sports Statistics
Elo ratings system developed by
Árpád
Élő
to
calculate relative skill levels of chess players
where:
R
N
= New rating
R
O
= Old rating
O =
Observed Score
E =
Expected Score
W
= Multiplier
(
16
for masters, 32 for lesser players
)Slide31
Probability Bands: Elo Ratings
31
RMIT University©2011
RMIT Sports Statistics
+Slide32
Probability Bands: Elo Ratings
32
RMIT University©2011
RMIT Sports StatisticsSlide33
33
RMIT University©2011
RMIT Sports Statistics
Probability Bands: Elo Ratings (2003-2010)Slide34
34
RMIT University©2011
RMIT Sports Statistics
Probability Bands: Elo Ratings (2003-2006)
+Slide35
35
RMIT University©2011
RMIT Sports Statistics
Probability Bands: Elo Ratings (2003-2006)
High variability in the majority of probability bands during the burn-in period.Slide36
36
RMIT University©2011
RMIT Sports Statistics
Probability Bands: Elo Ratings (2007-2010)
+Slide37
37
RMIT University©2011
RMIT Sports Statistics
Probability Bands: Elo Ratings (2007-2010)Slide38
Advantages and Shortcomings of SPARKS and Elo Ratings
38
RMIT University©2011
RMIT Sports Statistics
SPARKS considers the margin of the result, often a difficult task in the context of tennis;
Elo is only concerned with whether the player wins or loses, not the margin of victory in terms of the number of games or sets won;
Elo provides a more efficient model in terms of probability banding, suggesting that evaluating the margin of matches may be misleading at times.Slide39
www.rmit.edu.au/sportstats
Market Efficiency of ATP Tennis in
Recent YearsSlide40
ATP Betting Markets Used in the Current Analysis
RMIT University©2011
RMIT Sports Statistics40MarketAbbreviationBet 365
B365LuxbetLB
ExpektEX
Stan JamesSJ
Pinnacle Sports
PS
Elo
ratings
Elo
SPARKS
SPARKSSlide41
Overall Efficiency of Each Market between 2003 and 2010
RMIT University©2011
RMIT Sports Statistics41Market2003
20042005
20062007
2008
2009
2010
Overall
B365
.71
.67
.70
.71
.72
.71
.70
.70
.703
LB
.70
.69
.68
.69
.70
.71
.70
.70
.697
PS
.71
.65
.70
.68
.72
.70
.70
.70
.696
SJ
.69
.69
.70
.67
.73
.69
.70
.71
.696
EX
.72
.65
.72
.69
.73
.70
.70
.69
.698
Elo
.59
.62
.66
.65
.70
.66
.68
.67
.654
SPARKS
.63
.64
.69
.67
.66
.60
.69
.72
.667
Overall
.68
.66
.69
.68
.71
.68
.70
.70
.69
+Slide42
Overall Efficiency of Each Market between 2003 and 2010
RMIT University©2011
RMIT Sports Statistics42Market2003
20042005
20062007
2008
2009
2010
Overall
B365
.71
.67
.70
.71
.72
.71
.70
.70
.703
LB
.70
.69
.68
.69
.70
.71
.70
.70
.697
PS
.71
.65
.70
.68
.72
.70
.70
.70
.696
SJ
.69
.69
.70
.67
.73
.69
.70
.71
.696
EX
.72
.65
.72
.69
.73
.70
.70
.69
.698
Elo
.59
.62
.66
.65
.70
.66
.68
.67
.654
SPARKS
.63
.64
.69
.67
.66
.60
.69
.72
.667
Overall
.68
.66
.69
.68
.71
.68
.70
.70
.69Slide43
Overall Efficiency of Each Market between 2003 and 2010
RMIT University©2011
RMIT Sports Statistics43+Slide44
Overall Efficiency of Each Market between 2003 and 2010
RMIT University©2011
RMIT Sports Statistics44
Heightened stability and efficiency across markets and seasons since 2008.Slide45
Converting Market Odds into a Probability
RMIT University©2011
RMIT Sports Statistics45Novak DjokovicRafael Nadal
Match Odds$1.63
$2.25Conversion1/1.63
1/2.25Probability of Winning
.61
.44
2011 US Open FinalSlide46
Accounting for the Over-Round
RMIT University©2011
RMIT Sports Statistics46 The sum of the probability-odds in any given sporting contest typically exceeds 1, to allow for the bookmaker to make a profit; The amount that this probability exceeds 1 is referred to as the over-round;
For example, if the sum of probabilities for a given match is equal to 1.084, the over-round is equal to .084 or 8.4%Slide47
Accounting for the Over-Round
RMIT University©2011
RMIT Sports Statistics47Novak DjokovicRafael Nadal
Match Odds$1.63
$2.25Conversion1/1.63
1/2.25Probability of Winning
.61
.44
Sum of Probabilities
1.05
Over-Round
5%
2011 US Open Final
6 – 2 6 – 4 6 – 7 6 – 1 Slide48
Comparison of Over-Round Across Markets
RMIT University©2011
RMIT Sports Statistics48+Slide49
Comparison of Over-Round Across Markets
RMIT University©2011
RMIT Sports Statistics49Kruskal-Wallis test with follow-up Mann-Whitney U tests:Significant difference between all betting markets aside from Pinnacle Sports and Stan James.Slide50
Over-Round for Bet 365 (2003-2010)
RMIT University©2011
RMIT Sports Statistics50Slide51
Accounting for the Over-Round: Normalised Probabilities and Equal Distribution
RMIT University©2011
RMIT Sports Statistics51Novak Djokovic
Rafael NadalMatch Odds$1.63
$2.25
Raw Probability of Winning.61
.44
Over-round
.05
.05
Normalisation
.61/1.05
.44/1.05
Normalised Probability of Winning
.58
.42
Equal Distribution
.61 – (.05/2)
.44 – (.05/2)
Equalised Probability of Winning
.585
.415
+Slide52
Accounting for the Over-Round: Normalised Probabilities and Equal Distribution
RMIT University©2011
RMIT Sports Statistics52Novak Djokovic
Rafael NadalMatch Odds$1.63
$2.25
Raw Probability of Winning.61
.44
Over-round
.05
.05
Normalisation
.61/1.05
.44/1.05
Normalised Probability of Winning
.58
.42
Equal Distribution
.61 – (.05/2)
.44 – (.05/2)
Equalised Probability of Winning
.585
.415Slide53
Accounting for the Over-Round: Normalised Probabilities and Equal Distribution
RMIT University©2011
RMIT Sports Statistics53Roger FedererBernard Tomic
Match Odds$1.07$6.60
Raw Probability of Winning
.93
.15
Over-round
.08
.08
Normalisation
.93/1.08
.15/1.08
Normalised Probability of Winning
.86
.14
Equal Distribution
.93 – (.08/2)
.15 – (.08/2)
Equalised Probability of Winning
.89
.11
+Slide54
Accounting for the Over-Round: Normalised Probabilities and Equal Distribution
RMIT University©2011
RMIT Sports Statistics54Roger FedererBernard Tomic
Match Odds$1.07$6.60
Raw Probability of Winning
.93
.15
Over-round
.08
.08
Normalisation
.93/1.08
.15/1.08
Normalised Probability of Winning
.86
.14
Equal Distribution
.93 – (.08/2)
.15 – (.08/2)
Equalised Probability of Winning
.89
.11Slide55
Market Efficiency in ATP Tennis
RMIT University©2011
RMIT Sports Statistics55+Slide56
Market Efficiency in ATP Tennis
RMIT University©2011
RMIT Sports Statistics56
SPARKS significantly less efficient when compared with the betting markets for all bands aside from .50 - .55.Slide57
Market Efficiency in ATP Tennis - Raw
RMIT University©2011
RMIT Sports Statistics57+Slide58
Market Efficiency in ATP Tennis - Raw
RMIT University©2011
RMIT Sports Statistics58
General inefficiency across bands, likely due to no correction for the over-round.Slide59
Market Efficiency in ATP Tennis - Normalised
RMIT University©2011
RMIT Sports Statistics59Slide60
Market Efficiency in ATP Tennis – Equal Diff
RMIT University©2011
RMIT Sports Statistics60+Slide61
Market Efficiency in ATP Tennis – Equal Diff
RMIT University©2011
RMIT Sports Statistics61
Relative consistency in efficiency and variability within each band across markets.
+Slide62
Market Efficiency in ATP Tennis – Equal Diff
RMIT University©2011
RMIT Sports Statistics62
Evidence of
longshot
bias for the .25 to .30 band.Slide63
Market Efficiency in ATP Tennis: Bet365
RMIT University©2011
RMIT Sports Statistics63+Slide64
Market Efficiency in ATP Tennis: Bet365
RMIT University©2011
RMIT Sports Statistics64Slide65
Longitudinal Changes in Market Efficiency
RMIT University©2011
RMIT Sports Statistics65+Slide66
Longitudinal Changes in Market Efficiency
RMIT University©2011
RMIT Sports Statistics66
Few significant differences emerged when comparing efficiency across the bands over the past 8 years.
Homogeneity of variance tests revealed significantly less variability across markets in recent years. Slide67
Most Efficient Year: 2007
RMIT University©2011
RMIT Sports Statistics67+Slide68
Most Efficient Year: 2007
RMIT University©2011
RMIT Sports Statistics68Slide69
Least Efficient Year: 2004
RMIT University©2011
RMIT Sports Statistics69+Slide70
Least Efficient Year: 2004
RMIT University©2011
RMIT Sports Statistics70Slide71
www.rmit.edu.au/sportstats
Discussion of FindingsSlide72
Psychological Player Considerations
RMIT University©2011
RMIT Sports Statistics72 Form of an individual player will affect the context and potential outcome of the entire match, as opposed to a team-based sport where individual players have less impact or can be substituted off if out of form.
Micro-events within a match, at times, have an impact on the outcome of the match. Examples: Rain delays
Injury Time outs Code violationsSlide73
Shortcomings of the Current Analysis
RMIT University©2011
RMIT Sports Statistics73 A set multiplier of ‘6’ was used for the SPARKS model based on the original SPARKS model published in 2000; Only a limited number of betting markets were incorporated, and therefore it was not possible to utilise Betfair
data into the analysis; Differences in market efficiency and inefficiency were not evaluated at the surface level. This would be particularly interesting if evaluated for clay, given the volatility of player performance on clay when compared with other surfaces.Slide74
Future Work
RMIT University©2011RMIT Sports Statistics
74 Optimise the set multiplier of the SPARKS model; Develop a model that combines SPARKS and Elo ratings;
Extend the current findings to incorporate women’s tennis given that evidence has shown greater volatility in the women’s game.
Incorporate data on other potential predictors of tennis outcomes. Examples include: The set sequence of the match
Surface Importance of the tournament (e.g., Grand slams)Slide75
Conclusions
RMIT University©2011RMIT Sports Statistics
75 Whilst considerable variability was evident during the 2003 – 2007 seasons, an increase in consistency across markets since 2008. Following a lengthy burn-in period of four years, the Elo model outperformed SPARKS and most betting markets across the majority of probability bands;
Whilst not efficient in terms of probability banding, the SPARKS model was able to predict an equivalent proportion of winners to the betting markets, and outperformed some markets in recent years;
A model that combines both Elo and SPARKS may yield the most efficient model.Slide76
Questions and Comments
RMIT University©2011
RMIT Sports Statistics76Slide77
RMIT University©2011RMIT Sports Statistics
77