Goals Goals Goals

Goals Goals Goals

If you read my previous article you will be fully aware that I’m expanded my operations across Europe and that means I’ve having a crack at a couple of more leagues this weekend, in my pursuit to build the perfect predictive betting model.

However, this particular article is going to be a little different as this time, I am going to look not at results but just goals and with another data driven betting approach, I am now going to try and predict the Over/Under market for this weekend in the English Premier League.

How Does It Work?

Now that ‘GoalBot’ has been born, I will now explain how it works:

Take the percentage of matches the home team has played in, that has ended in a total of over 2.5 goals being scored in (this season) + Take the percentage of matches the away team has played in, that has ended in a total of over 2.5 goals being scored in (this season) and then divide by 2.

If the percentage is over 50% return an answer of Over 2.5
If the percentage is under 50% return an answer of Under 2.5

And with that method in mind, here are the first wave of weekend predictions from ‘GoalBot’

As you can see they have been ranked in the likelihood from top to bottom (also listing the Over/Under likelihood) and as you can see, there are some games that look all the more likely of the correct outcome happening.

For example. if we look at the polar opposites of the spectrum we can see that the games at the Etihad and Bramall Lane will more than likely end up in the way they’ve been predicted. Although we probably need to allow for some form of margin of error

Because the split is 50/50 it’s probably a bit too linear, so lets also say that any Over pick which is less than 55% and any Under pick is less than 45% is one that we do not touch because it could be a little too close for comfort.

Therefore let’s rule out the Watford vs Burnley, Brighton vs Leicester and Everton vs Norwich fixtures from our potential lists of games to choose from on the Over/Under 2.5 goals accumulator slip.

Which means what else should we be opting for:

Manchester City vs Chelsea – Over 2.5
Sheffield United vs Manchester United – Under 2.5
Bournemouth vs Wolves – Under 2.5
Any of the four games that are on 58.33% return for Over 2.5

For the sake of argument let’s go with Crystal Palace vs Liverpool on this one and therefore I will offer this four-fold for the weekend:

Manchester City vs Chelsea – Over 2.5
Crystal Palace vs Liverpool – Over 2.5
Sheffield United vs Manchester United – Under 2.5
Bournemouth vs Wolves – Under 2.5

Now usually I aim to predict every game correct in a particular division, but as we are going on a goal only method, I am going to offer this one as a straight tip and it is one that if you were to back four-fold, will pay out odds of around 5.5/1. (Warning this is just a first week of this kind of modelling, so all bets at your own risk).

Ultimately this model is its infancy and  there might be a bit of tweaking that still needs to be done – therefore I am going to base my success on correct tips and no actual money involved, a little bit boring to start with but it at least keeps a roof over my head this season.

No doubt if it is a success, I will kick myself and bemoan not placing a bet and even though you say you lose 100% of the bets you don’t make, that particular mindset is one that can be a little dangerous. Anyway enough of the lecture, let’s see how this one pans out this time next week.

Happy punting and thanks for reading. Dan

 

If this has grabbed your interest and you would like to discuss/feedback then please feel free to drop me a message at [email protected]. While I am always looking for new football/data projects to work on and if you feel that my skills would be of use, I can be contacted at the same address.

Follow me on Facebook at Dan The Stat Man
You can also check out my Premier League Podcast on Soundcloud