Asian Cup Predictions Matches Case Study

Asian Cup Predictions

Asian Cup Predictions Matches Case Study

Asian Cup Predictions – Introduction

International football tournaments are notoriously difficult to predict.

Not only do teams who many not have faced each other for years play each other, often at a neutral venue, but the turn over of players from one match to the next can be significantly higher to what is seen in club football.

Compounding this already difficult situation is the collation of accurate and reliable statistics about teams and their previous matches. While it’s certainly not the same as 50 years ago when players never have seen outside of their home country would suddenly appear at a World Cup, but it is much easier to obtain in-depth statistics about Brazil vs Germany than it is for Malaysia vs Fiji.

In this case study we will apply two different predictive models to the 2015 Asian Cup to see how accurately they can predict matches with limited data, and compare their accuracy in predicting the match winner to bookmakers.

Selection of sample Asian Cup teams
For the purposes of the case study two of the four groups involved in the Asian Cup were used, with each group stage match modeled and analysed. The groups selected are groups A and D.

These groups were chosen due to the difference in statistics available for the eight participating teams. Tournament heavyweights Japan, South Korea and hosts Australia all have extensive match and player statistics available, while minnows Palestine had as few as five matches to base predictions with.

The two groups also provide an interesting balance of teams who competed at the World Cup in the last calendar year (Japan, South Korea and Australia), through to a side who was required to come through a qualifying tournament (Palestine).

Asian Cup Predictions – Match prediction models

Two different models were applied to each group match for pools A and D of the tournament. The first, Total Shots Ratio (TSR), hoped to identify the “better” attacking team (and therefore the most likely to win), while the second will use a power ranking system known as the World Football Elo Ratings to calculate match probabilities.

Both TSR and the Elo Ratings will be compared to the bookmaker favorite to see which more accurately predicts the winner of each match. The Elo Rating’s match probabilities will also be used to identify potential value bets throughout the tournament.

Asian Cup Predictions – Total Shots Ratio

To calculate the TSR of each of the eight participating teams, shots for, and shots against were obtained from Soccerway. For the case study data from up to a maximum of 20 matches was collected from the years 2013 and 2014.

With shot data not available for all matches these were not always sequential, and the total number of samples differed from team to team (for example only five samples were available for Palestine). This data will however be updated through out the tournament.

The application of TSR in a tournament setting compared to a league has one obvious problem, the goals scored and conceded by different nations were against teams of varying abilities.

For example within their 20 matches Australia were defeated by both Brazil and France 6-0, while fellow group A competitors Kuwait and Oman rarely played outside of Asia. TSR also does not take into account the standing of the respective matches, a friendly has the same weighting as a World Cup final in the rating calculation.

Inside a league setting where teams play the same teams multiple times this is not a problem and it would be expected that the modeling would be more accurate. Through this case study we hope to see if this also applies in a tournament setting.

There are also questions about TSR’s real assessment of a team’s attacking ability. Without a way to assess the quality and context of each shot TSR can potentially lead to a false assessment of a team’s true goal scoring potential.

Asian Cup Predictions – World Football Elo Ratings

The Elo Ratings used in the case study will come directly from the World Football Elo Ratings website, with ratings updated between each match.

Where TSR’s achilles heel is its inability to distinguish between different levels of match and opponent, Elo Ratings are purely based on these factors. The stronger the opposition you beat, the higher your rating becomes. Similarly, losses against highly rated opponents are not punished as harshly as those against teams you are expected to beat.

It should also be noted that there is a ratings boost in probability calculations with Elo Ratings, this will be applied to Australia throughout the tournament.

Pre-tournament ratings

Asian Cup Group A

Team Elo Rating TSR Rating Bookmaker probability to win group*
Australia 1635 0.48 58%
Korean Republic 1619 0.56 44%
Kuwait 1513 0.44 6%
Oman 1543 0.44 7%

  • Quoted odds to win Group A with Bet Easy

Pre-tournament group A was expected to be dominated by hosts Australia and the Korean Republic by bookmakers. This was mirrored in the Elo Ratings with both rated substantially higher than Kuwait and Oman. TSR suggests that Koran are the strongest attacking team in the group, while Oman are expected by both the bookmakers and Elo to finish third in the group.

Asian Cup Group D

Team Elo Rating TSR Rating Bookmaker probability to win group*
Iraq 1498 0.45 13%
Japan 1712 0.55 83%
Jordan 1509 0.46 13%
Palestine 1322 0.45 2%

  • Quoted odds to win Group D with Bet Easy

Japan are dominant favourites to win the group on all three models, and are the strongest team in the tournament according to the Elo Ratings. There is little to separate Iraq and Jordan on any of the measures as they look likely to battle out second placing in the group. Palestine are by far the weakest team according the the Elo Ratings and bookmakers, however interestingly have a similar TSR to Iraq and Jordan.

Asian Cup Predictions – Match Results

At the conclusion of the two weeks of the group phase of the tournament, all three models correctly predicted at least 75% of winners. This may have been aided by the lack of draws seen throughout the tournament as a whole, with all 24 matches during the group stage having a winner.

Predictive Model Selections & Results

Match TSR Prediction Elo Prediction Bookmaker Prediction Winner

  • Australia v Kuwait
  • Korean Republic v the Oman Korean
  • Japan v Palestine
  • Iraq v Jordan
  • Australia v Oman
  • Korean Republic v Kuwait
  • Palestine v Jordan
  • Iraq v Japan
  • Australia v Korean Republic
  • Oman v Kuwait
  • Japan v Jordan
  • Iraq v Palestine
  • Total Correct 9/12 10/12 11/12 x
  • Win Percentage 75% 83% 92% x
  • Within the sample of 12 matches, only on three occasions did the models differ in their opinion of who the match-winner would be. Interestingly, when all three models were unanimous in their choice of the strongest team the team saluted nine out of nine times.

Only on one occasion did both the Elo Rating and TSR disagree with the bookmaker favourite (Jordan over Iraq). While both Elo and TSR had the teams as almost exactly equal, they did both slightly favour Jordan however bookmaker favourite Iraq ultimately won the match 1-0.

On two occasions the TSR disagreed with both the Elo Ratings and bookmakers on which was the better team. In the first match, the Korea stunned Australia winning 1-0, while in the second example Kuwait were selected to defeat Oman (with Oman winning).

Overall the bookmaker’s favourite was the most successful in selecting the winner of matches with an amazing 92% strike rate. Blindly level stake betting the bookmaker favourite in each match would have netted a return of 44% over the tournament.

The second most accurate model was the Elo Ratings, selecting the winner in 83% of matches. Blindly level stake betting the top rated team using the Elo Ratings would have netted a return of 22%. Perhaps more interestingly though, betting only when an edge was identified through the expected win percentage an 9% return was achieved using level stakes.

The least accurate of the models was the Total Shot Ratio which predicted the winner in 75% of matches. Unsurprisingly betting blindly at level stakes also achieved the lowest return of 2%.

Asian Cup Predictions – Conclusion

With so many international football tournaments each year at a range of different age groups there are many situations were punters may be required to handicap matches involving sides with little form, and with a high degree of mystery surrounding the participating teams and players.

This lack of data, or data which may be against a variety of different quality opposition can make modelling very difficult. Our pure team statistic based model, Total Shot Ratio was the lowest performing of the three models, however with such a small sample of matches it is hard to definitively rule it out completely as a tool to identify winners.

It was the only model to find the victory for Korea over the Socceroos, however this could be explained away as Australia were resting a number of players. It also incorrectly predicted Kuwait as a better attacking team to Oman which could be due to the differing levels of opposition the teams have faced in their previous 20 matches.

The Elo Ratings only major stumble was selecting Jordan to defeat Iraq in the opening round (albeit by only 1%). Its only other selection which lost, Australia to Korea, was easily explainable and was also incorrectly predicted by the bookmakers.

For me the Elo Ratings real party piece of the tournament was its ability to find six value bets (four wins and two losses), during the tournament. With level stake betting these returned a very reasonable 9% profit.

Yes this was less than simply betting both the Elo Ratings and bookmaker favourites blindly, however simply blind betting is not a sustainable strategy long term as its not known at any stage what the expected value of any bets are.

So if your looking for a football match prediction model for an upcoming tournament where stats are few and far between look to the bookmakers to give you the greatest lead on which team is more likely to win. However through the use of a power ranking system like Elo Ratings you might just find an exploitable edge in their prices.

Asian cup predictions match case study round one

After a long wait, the Asian Cup finally kicks off this Friday in Melbourne as hosts Australia face Kuwait. As part of our football predictive model case study, we preview each of the opening round Asian Cup matches to see who we, and the bookmakers think will win each of the matches in Groups A and D.

Don’t forget to read our introductory article about the case study, and check back regularly to not only see how our predictions compare but for our predictions for all group phase matches.

Australia v Kuwait match prediction

Asian cup predictions

Result Total Shot Ratio Elo Win Expectancy
Australia 0.48 78% 1.27
Draw x x 5.58
Kuwait 0.44 22% 14.49
Prediction Australia Australia Australia
Unsurprisingly at home against minnow Kuwait, the Socceroos are strong favorites to claim victory in the opening match of the tournament. Rated $1.28 through our Elo Ratings it seems as though the bookmakers agree with our two model’s assessment of the match.

The Korea Republic v Oman match prediction

Result Total Shot Ratio Elo Win Expectancy
Korea Republic 0.55 60% 1.57
Draw x x 3.90
Oman 0.43 40% 7.08
Prediction Korea Republic Korea Republic Korea Republic
Again all signs point to the favourites in the second match of Group A. Interestingly, South Korea had the best TSR from all 8 teams in our case study, but the third best Elo Rating, suggesting that their recent shots may have come either in losses, or against weak opposition. Rated at $1.66 by our model they seem overvalued by Pinnacle.

Japan v Palestine prediction

Result Total Shot Ratio Elo Win Expectancy
Japan 0.54 90% 1.15
Draw x x 8.33
Palestine 0.45 10% 22.57
Prediction Japan Japan Japan
Qualifiers Palestine aren’t expected to trouble reigning Asian Champions Japan. Amazingly the Blue Samurai are actually a value bet at $1.15 with Pinnacle according to our Elo Ratings.

Jordan v Iraq prediction

Jordan vs Iraq

Result Total Shot Ratio Elo Win Expectancy
Jordan 0.45 51% 3.12
Draw x x 2.97
Iraq 0.44 48% 2.64
Prediction Jordan Jordan Iraq
In a match that is likely to decide who progresses to the elimination stage of the tournament, both of our models are predicting a victory to Jordan by the slightest of margins. Rated a $1.96 chance Jordan does seem value but there is so little between the teams it is hard to recommend betting on them in the first test of whether our models are better at predicting winners than the bookmakers.

Asian Cup Predictions Case Study Round 2

One round down and we are quickly onto the second round of matches for the Asian Cup. In this article, we will post an update on our match prediction case study and see how our predictions have fared so far and look forward to the next four matches.

Results so far
Match TSR Prediction Elo Prediction Bookmaker Prediction Winner
Australia v Kuwait Australia Australia Australia Australia
Korean Rupublic v Oman Korean Republic Korean Republic Korean Republic Korean Republic
Japan v Palestine Japan Japan Japan Japan
Iraq v Jordan Jordan Jordan Iraq Iraq
x x x x x
Total Correct 3/4 3/4 3/4 4/4
The first round of matches went largely to script for both groups as three of the tournament heavyweights faced off with minnows. Bookmakers Pinnacle Sports correctly found the winner in all four matches which was an impressive start. Both the TSR and Elo rating incorrectly selected Jordan to defeat Iraq, however there was very little difference between both sides ratings.

The only value bet identified by the Elo ratings was a winner with Japan easily accounting for Palestine.

The Korean Republic v Kuwait match prediction

Result Total Shot Ratio Elo Win Expectancy
Korean Republic 0.56 69% 1.452
Draw x x 4.450
Kuwait 0.43 31% 8.570
Asian Cup Predictions – Prediction Korean Republic
No surprises with both models and bookmakers all expecting a win for the Koreans in their second match in Canberra in four days. The current price available with Pinnacle Sports is exactly the same as the Elo win expectancy, while they have a much higher TSR than Kuwait who was brave in the tournament opener.

Australia v Oman match prediction

asia cup predictions

Result Total Shot Ratio Elo Win Expectancy
Australia 0.49 78% 1.375
Draw x x 4.970
Oman 0.42 33% 9.780
Asian Cup Predictions – Prediction Australia
At their current price of $1.38 hosts, Australia is providing value according to the Elo win expectancy. The Socceroos also have a higher TSR. Oman was impressive in their opener against Korea, however are given little chance against the hosts by bookmakers.

Palestine v Jordan match prediction

Result Total Shot Ratio Elo Win Expectancy
Palestine 0.37 27% 9.190
Draw x x 4.279
Jordan 0.45 73% 1.454
Asian Cup Predictions – Prediction Jordan
Another strong favorite with qualifiers Palestine meeting Jordan who went down in a close encounter with Iraq in their first match of the tournament. Rated a $1.37 chance by our Elo Rating, Jordan is value at the $1.454 currently available with Pinnacle Sports.

Iraq v Japan match prediction

Result Total Shot Ratio Elo Win Expectancy
Iraq 0.45 33% 11.000
Draw x x 4.750
Japan 0.56 67% 1.370
Asian Cup Predictions – Prediction Japan
Tournament favorites Japan meet first-round winners Iraq in the final match of the second round. All signs point to another victory by Japan, however, the Elo Ratings suggest it could be a much closer affair than the bookmakers are predicting.

Rated a $3 chance by our model, Iraq seem great value at $11 (however are not a suggested bet as our model does no include the draw), while Japan are currently overvalued with our model rating them at $1.49.

Asian Cup Predictions Case Study Round 3

We quickly move onto the final round of the group stage of our tournament betting case study with some close and heavyweight clashes. Don’t forget to read our introductory article, and our previews for round 1 and round 2 of the tournament so far.

Results so far
Match TSR Prediction Elo Prediction Bookmaker Prediction Winner
Australia v Kuwait
Korean Republic v Oman
Japan v Palestine n
Iraq v Jordan
Australia v Oman Australia Australia Australia Australia
Korean Republic v Kuwait
Palestine v Jordan
Iraq v Japan
x x x x x
Total Correct 7/8 7/8 8/8 x
Asian Cup round 3 predictions
Asian Cup Predictions – Prediction Korean Republic

Result Total Shot Ratio Elo Win Expectancy
Australia 0.52 66% 2.02
Draw x x 3.14
Korean Republic 0.56 47% 4.14
Asian Cup Predictions – Prediction Korea
Its the clash everyone had circled in their calendar as soon as the groups were announced for the tournament and host Australia face fellow Asian heavyweights the Korean Republic. This game is the first with different teams with higher TSR and Elo Ratings. This is also the first match with a major difference in the Elo win expectancy and prices available from bookmakers, however, they do agree that Australia should win the match.

Oman v Kuwait prediction

Result Total Shot Ratio Elo Win Expectancy
Oman 0.40 52% 2.36
Draw x x 3.27
Kuwait 0.44 48% 3.33
Asian Cup Predictions – Prediction Kuwait
Again the TSR and Elo Ratings differ in their highest ratings, while the Elo win expectancy and bookmakers agree. With both teams without a point it the match has no impact on the group results however will certainly help to separate our two models.

Japan v Jordan prediction

Result Total Shot Ratio Elo Win Expectancy
Japan 0.56 78% 1.353
Draw x x 5.120
Jordan 0.48 22% 10.450
Asian Cup Predictions – Prediction Japan
Both teams will be desperate to win their final match, for Japan a win locks up 1st place in the group, while a win for Jordan will keep them in contention for 2nd place. Again there seems to be value for the favorite, rated at $1.28 by the Elo win expectancy.

Iraq v Palestine prediction

Result Total Shot Ratio Elo Win Expectancy Pinnacle
Iraq 0.44 78% 1.256
Draw x x 6.400
Palestine 0.34 22% 12.800
Asian Cup Predictions – Prediction Iraq
Iraq is strong favorites to claim their second win of the tournament against Palestine. The bookmakers have them priced very similar to our Elo win expectancy.

Leave a Reply