During this years summer vacation I had the idea to get back to some work I did a few years back. I am speaking of my analysis of the European Football Betting Market I did for my BA thesis. The basic idea was to test the “Efficient Market Hypothesis” using as much football data from the most important leagues in Europe I could get my hands on back in the days.

I always liked the thrill from betting on soccer games. But after some very boring seasons in Germany (thank you very much FC Bayern Munich), I pretty much lost the interest in watching and betting.

So I sat down and asked myself, if I could find any reliable strategy to use for next season. I started to gather some data and write down python code in a jupyter notebook. I decided to devide the analysis into two parts:

  1. Part one will cover getting the data, looking at the data set, data wrangling and arbitrage analysis
  2. In part two I will check on the most widespread strategies in football betting (i.e. the famous favourite longshot-bias)

You can find the part one jupyter notebook on my GitHub.

I am thankful for any remarks and comments, just feel free to message me via email.