So, to sum the last two posts up. The lower the delta, the fewer rounds to predict – the better the model is at projecting the table positions and how many points a team will get. The easiest way of visualizing would be to look at how well the model performs in terms of correctly guessed table positions or near table positions. Continue reading Projecting league positions, part 3 – Allsvenskan!
This post turned out to become quite a lot related to programming. As I mentioned in the last post my idea was make my predictive table positions/points model more accurate by adding more data to it. I wanted to use my own football-data parser in order to add shots data, including TSR to all teams included in the model.
With the Swedish leagues slowly coming to an end I wanted to look at creating a method for making a qualified, statistically based projection of how football leagues will end up. As the name of this blog now implies, I have approached the problem with machine learning and the results look really promising!
Just as we thought that MFF was going to start moving upwards in the Allsvenskan table they lost to BK Häcken. Could it be that they have their mind set on the big game coming up against Celtic?
Some time ago I got a question from Tom Worville, at http://analyticsfc.co.uk/ if I could share how I create my plots. As I have mentioned before I use Plotly. In my opinion a superb visualization tool with a great api and a sound user policy. Being a Python programmer their eminent python library is of course extra appreciated.
Here is how I create a football pitch with Plotly. Meet footballpitchplot!
So, I thought I’d answer two questions in this blog post.
The first was a question from an article in Östersundsposten this week, asking who you think is the best player ever to have played in ÖFK.
The second was a question I got when I wrote about Lasse Vibe and his efficiency in terms of his ratio between expected goals and actual goals.
Now, the answer to the two questions turned out to be related and make one blog post.