Predictor Version 3

Version 3
The new predictive element I have calculated to be the best to use is a logistic regression machine learning element to predict result of a match. Followed  by taking the average xG scored and conceded by both the home and away team to produce an average value for the home team to score and away team to score which then uses a Poisson distribution with these numbers as mean to find the most likely score line with matching result to the first element.

Naive Bayes and Results was selected by testing performance against 3 other predictors that use either Bayes or Logistic regression to predict either scoreline or result. The performance test was accuracy of predicting the correct result even if scoreline was used to train the data as ultimately that is what they are both trying to predict.

Results shown below:
ML\Predict Results Score
Bayes 0.47 0.31
Logistic 0.50 0.47

So this is only a small improvement from the old version 2 predictor which got 0.46 but this predictor is still in its first stages and the attributes and data it is being fed are the ones I found optimal for my linear regression model. For example the linear regression model was able to build a relationship between different attributes such as form whereas the classifier views home form and away form entirely separately if 2 teams both have 15/15 form it'll suggest they both align with the category where that team wins and in affect cancel out. So hopefully by changing the relationships and feeding it slightly different attributes this predictor can be pushed further.

The other improvement still to be made is in calculating the means to be used for the Poisson distribution estimators. Currently home average cored and away average conceded are just added and divided by 2 but this may not be the relationship between these variables. It is a logical place to start as you would expect the actual number scored to be half way between what the home team can score and the away team will concede so will do for now. But it may be worth using another machine learning model, probably linear regression to predict team scoring based on these variables.

https://github.com/calumdee/predictorv3

Comments

Post a Comment

Popular posts from this blog

The problem with xG totals

There has been several reports in the media suggesting that despite Town’s impressive first half performance against West Ham they were in fact lucky to get a point in the end due to a number of high quality chances given away. Now when you look at the xG totals from the game it would seem to back this theory up with the xG score being: 1.19-2.04. The only problem here with these totals is that they take all context out of the individual chances when summing them up, it assumes all chances are independent for the relation to hold. Take Hernandez’s double chance just after half time where he takes a shot from close range which is saved before putting a header over the bar. Now he generates an xG of 0.49 and 0.57 for these two chances respectively, which would suggest that he has a 22% chance of not scoring, 50% chance of scoring once and a 28% chance of scoring twice. Although this can’t be true because how could he have scored two goals in that time there was only 1 second between ...
Read more

Premier League Predictions 11

Image
Each week I am going to try and remember to post my ML premier league predictor's predictions for the round of fixtures and keep track of how well it is doing in terms of correct results and scores. I will also be including a track of money won and lost if each predicted result was bet on. This will be done using my v2 for now but will transition to v3 when it is complete. I am starting 10 weeks in to the season as most teams have now played 5 home and 5 away games and thus the attributes fed to the machine learning algorithm should be fully populated and give more sensible predictions. Due to the way it is set up in very early weeks attributes like form can behave weirdly if a team has 0 points and another max even if it has only been 1 game. For comparison, so far the predictor has 51 results correct of which 7 of these have been correct scores. Betting £1 on each game's predicted result would have yielded a profit of £5.01 so far not including stake. Week 11 Prediction...
Read more

Does time of shot affect affect xG?

A major decision for managers of smaller clubs, who can’t just blow opposition teams away, is whether to go out quick at the start and try and get an early lead, then defend it or to keep it tight, before throwing everything at the wall for the last period of the match to try and snatch it at the death. Both methods have their benefits; the early attack gives more time to get the goal, but there’s no definitive end point as to when to start shutting up shop if the goal can’t be found as it’s unlikely a team would be able to keep up the intensity for a whole match. The late attack gives you more defensive security, as you prioritise not conceding in the early stages but can backfire if your opposition is fitter and have more in the tank at the end. What if it was possible to tell when is best to attack based purely on xG, if it could be shown that the time in the match affected how likely a shot was to be scored? It could help to decide when to attack to get the most out of it, or wh...
Read more