Predicting Football Matches using Machine Learning

Using the previous machine learning model, I am going to predict this Wednesday match result. Running my model gives:

Real Madrid vs Manchester United

  • Probability of draw is 0.9993.
  • Probability of Real Madrid winning against Manchester United is 0.5074.

  • Since the probability of draw is very high, it is very likely that the match will end until penalty kicks. The score difference will be 1.

Tottenham vs Milan

  • Probability of draw is 0.999.
  • Probability of Tottenham winning against Milan is 0.513.

  • Same as above, I suspect the match will end with penalty kicks. Score difference is 1.

Barcelona vs Roma

  • Probability of draw is 0.999.
  • Probability of Barcelona winning against Roma is 0.512.

  • Same as 1 and 2. Score difference is 1.

Currently, the model is based on each team’s ranking. It does not take into account individual player’s ranking. I am excited to see the results.


MU vs RM : 2 – 1

T vs M : 1 – 0

B vs R : 2 – 4

The model is 2/3 correct. I was not expecting Roma to win against Barcelona. Next time, I should take into account of all 11 players’ ratings in the model.

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s