Sports analytics is a fascinating topic and I have written about it many times, and also released courses in that area, in topics such as how to predict sports outcomes.
A particularly interesting piece of work I did in the past was to study the use of machine learning for predicting cricket games. It seems that using the right features and algorithms it is possible to predict the outcome of cricket games well enough to beat the bookmaker odds. You can read more about it on the original paper at arXiv: http://arxiv.org/abs/1511.05837.
I am copying and pasting the abstract below:
“Cricket betting is a multi-billion dollar market. Therefore, there is a strong incentive for models that can predict the outcomes of games and beat the odds provided by bookers. The aim of this study was to investigate to what degree it is possible to predict the outcome of cricket matches. The target competition was the English twenty over county cricket cup. The original features alongside engineered features gave rise to more than 500 team and player statistics. The models were optimised firstly with team features only and then both team and player features. The performance of the models was tested over individual seasons from 2009 to 2014 having been trained over previous season data in each case. The optimal model was a simple prediction method combined with complex hierarchical features and was shown to significantly outperform a gambling industry benchmark.”
Just check the figure below to see the superiority of the model over the bookmaker odds.
If you are interested about the topic of sports prediction and sports analytics in general make sure to check my posts, and also my courses.