I have to put out a correction of my last blog post. Sorry about that! The impact of scoring the first goal wasn’t as large as I stated yesterday. I had a bug in my script that made erroneous game-states on goals scored. I have now corrected it and carefully checked the results. Thanks to the comment from Sam in the blog post I now also can compare the figures for Premier League which feels comforting. This is what the plot actually should look like:
Continue reading The (true) importance of scoring the first goal.
To quote coach Lars Lagerbäck – “Goals change games”.
At first, this post was just going to be a brief follow up of the preview I posted last week before ÖFK – Sirius. Well, the problem was that when I made the XG map after the game it just didn´t seem to make sense.
Continue reading The importance of scoring the first goal
So with the decisive game of Superettan just two days away I thought I’d make a detailed match preview. If ÖFK avoids a loss, the top two spots, leading to advancement seems to be more or less totally secured. So how large are the chances of Sirius making an upset on Saturday? Well, the easy answer would be to ask my predictive model, which I will describe more in coming blog posts. That model gives Sirius a 17.5% chance of winning. Why? Let’s look att the key numbers behind that calculation.
Continue reading Preview ÖFK – Sirius
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.
Continue reading Projecting league positions, part 2
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!
Continue reading Projecting league positions, part 1