Football fans cleverer than Betfair, apparently

Football, Soccer - whatever you call it. It is the beautiful game.
Post Reply
User avatar
mjmorris335
Posts: 180
Joined: Mon Jun 06, 2016 11:29 am

https://www.thetimes.co.uk/article/foot ... -kzc9ghf02

Article is behind a paywall but you get a few free articles a month if you register your email address.

Mike
User avatar
Euler
Posts: 24700
Joined: Wed Nov 10, 2010 1:39 pm
Location: Bet Angel HQ

New research shows that Twitter activity can help predict the result of football matches when combined with betting market prices.

The tone of Twitter posts can predict when a team is more likely to win and soccer bets are mispriced, the study by the University of East Anglia (UEA) found.

Researchers examined 13.8 million tweets - an average of 5.2 tweets per second - during an English Premier League (EPL) season. These were compared with in-play betting prices available at the same time on Betfair, the world’s largest online betting exchange.

They found that if the combined tone of tweets in a given second during a match was positive – as measured by a micro-blogging dictionary – then the team was more likely to win than the betting market prices implied.

Tweets were particularly informative in the aftermath of goals and red cards, suggesting that social media content is particularly useful in assessing the implications and significance of new information.

Social media is used as a forecasting tool by a variety of firms and agencies, but the researchers wanted to find out how useful and accurate it is. They measured the aggregate tone of all tweets for each team, in each second of 372 matches that took place during the 2013/14 season.

The study, published today in the journal Economic Inquiry, was conducted by Dr Alasdair Brown, of UEA’s School of Economics, and colleagues at the Universities of Dundee and Reading, and Birkbeck, University of London.

Dr Brown, a senior lecturer in economics, said: “The modern forecaster has a number of tools at their disposal. In particular, prediction markets and social media have proved extremely popular.

“We know that prediction markets, such as Betfair, generally lead to accurate forecasts, and outperform individual experts and polls in many settings. However, we wanted to find out if social media has anything to add. Can we combine probability forecasts from prediction markets with social media output to improve our predictions?

“We find that Twitter activity predicts match outcomes, after controlling for betting market prices. Much of the predictive power of social media presents itself just after significant market events, such as goals and red cards, where the tone of Tweets can help in the interpretation of information.

“In short, social media activity does not just represent sentiment or misinformation. If sensibly aggregated it can, when combined with a prediction market, help to improve forecast accuracy.”

The researchers constructed a number of betting strategies to quantify the degree of mispricing that social media predicts. Using conservative estimates of the commission paid to Betfair, and a strategy of betting when Tweets on a team are positive, a bettor could have earned an average return of 2.28 per cent from 903,821 bets. This compares favourably with average returns of -5.41 per cent across the matches studied.

Dr Brown said these were significant returns given the size of the Betfair betting market for EPL soccer matches, the very short horizon - less than 90 minutes - of the holding periods for most bets, and the fact that bets usually have negative expected returns.

The authors also wanted to examine whether tweets were particularly informative before a goal was scored, in which case this would suggest that social media users break news faster than betting/prediction markets. However, they found no evidence of this.

“These results fit in with recent evidence that social media content can be useful as a forecasting tool,” said Dr Brown. “For example, there is evidence that social media output, both on Twitter and on financial message boards, predicts future stock returns.

“At first glance this may be surprising, as we might think that an individual in possession of valuable information would bet or trade first, and post later. However, if we think that valuable information is dispersed among a number of individuals, then we might understand why social media content leads market prices, as it does in this study and elsewhere.”

Dr James Reade, sports economist at the University of Reading and a co-author of the study, said: “This is a real 'wisdom of crowds’ kind of outcome. It says that if we listen to the right parts of the crowd, we can gain more information and make better predictions.

“It’s great for football fans, who always want to know what others think of their team. Betting prices, allied with the general mood on Twitter, can give a really accurate picture of where a match is going, in real time.”

‘Forecasting with Social Media: Evidence from Tweets on Soccer Matches’, Alasdair Brown, Dooruj Rambaccussing, J James Reade and Giambattista Rossi, is published in Economic Inquiry on Friday October 13.
User avatar
3virgul14
Posts: 84
Joined: Wed May 26, 2010 8:28 am
Contact:

Sorry Peter but absolute bollocks :geek: :!:
User avatar
Euler
Posts: 24700
Joined: Wed Nov 10, 2010 1:39 pm
Location: Bet Angel HQ

I wasn't endorsing it but put it here to discuss.
User avatar
LeTiss
Posts: 5386
Joined: Fri May 08, 2009 6:04 pm

Euler wrote:
Fri Oct 13, 2017 3:11 pm
I wasn't endorsing it but put it here to discuss.
He has discussed it, he thinks it's absolute bollocks
User avatar
ShaunWhite
Posts: 9731
Joined: Sat Sep 03, 2016 3:42 am

LeTiss wrote:
Fri Oct 13, 2017 3:48 pm
Euler wrote:
Fri Oct 13, 2017 3:11 pm
I wasn't endorsing it but put it here to discuss.
He has discussed it, he thinks it's absolute bollocks
:lol:
"a strategy of betting when Tweets on a team are positive, a bettor could have earned an average return of 2.28 per cent from 903,821 bets. This compares favourably with average returns of -5.41 per cent across the matches studied."

So it's better than random then? And backing everything comes out at -5% (the commish, and 900k bets shows the market is 'correct') Is there any comparison to someone who's actually clued up more than the average twitter chimp?

Conclusion: When people think it's going well, it sometimes is. Who'd have thought it.

These social meja big data types are sooo clever at finding the patently bleedin obvious and selling it like it's news.
User avatar
Kafkaesque
Posts: 886
Joined: Fri Oct 06, 2017 10:20 am

ShaunWhite wrote:
Fri Oct 13, 2017 4:12 pm

:lol:
"a strategy of betting when Tweets on a team are positive, a bettor could have earned an average return of 2.28 per cent from 903,821 bets. This compares favourably with average returns of -5.41 per cent across the matches studied."

So it's better than random then? And backing everything comes out at -5% (the commish, and 900k bets shows the market is 'correct') Is there any comparison to someone who's actually clued up more than the average twitter chimp?

Conclusion: When people think it's going well, it sometimes is. Who'd have thought it.

These social meja big data types are sooo clever at finding the patently bleedin obvious and selling it like it's news.
The possible point to be sceptical of is, how their methodology is regarding what defines a "positive" tweet, as it's in no way defined (at least in the article). In reality, they could have run 1000 definitions of "positive" and cherrypicked the one with the best result to get coverage.

However, taking a very good return over close to a million on average and calling it sometimes is pretty far off base imho ;)

Betting is in its essence about being better than random picks (by more than the juice/commission), so I'm failing to see how it showing a better result than random disqualifies it?
User avatar
ShaunWhite
Posts: 9731
Joined: Sat Sep 03, 2016 3:42 am

Kafkaesque wrote:
Fri Oct 13, 2017 5:01 pm
However, taking a very good return over close to a million on average and calling it sometimes is pretty far off base imho ;)
I was using the never/sometimes/always scale ;)
Kafkaesque wrote:
Fri Oct 13, 2017 5:01 pm
Betting is in its essence about being better than random picks (by more than the juice/commission), so I'm failing to see how it showing a better result than random disqualifies it?
That's a fair point.

But if there is something in it, someone with deep pockets will weaponise that knowledge, and strip out that 2%.
You could say it's almost Kafkaesque ;)
Post Reply

Return to “Football trading”