## Predicting the beautiful game
[Octosport](https://www.octosport.io/) and [Sportmonks](https://www.sportmonks.com/) are proud to present their first football prediction competition. Do you know how to code in python and are passionate about football? Do you want to test your knowledge in machine learning, sequence learning, or neural networks? Do you want to beat the bookmaker's performance? You are at the right place.

## Competition Description

Football has been at the heart of data science for more than a decade. If today's algorithms focus on event detection, player style, or team analysis, predicting the results of a match stays an open challenge.

Predicting the outcomes of a match between two teams depends mostly (but not only) on their current form. The form of a team can be viewed as their recent sequence of results versus the other teams. So match probabilities between two teams can be different given their calendar.

This competition is about **predicting the probabilities** of more than **150000** match outcomes using the recent sequence of 10 matches of the teams.

## Community
As a part of the community competition, we want to encourage published notebooks. So **the best-published notebook will also be rewarded**. See the prizes section for more information.

## Benchmark
To add more fun we also added the performance of the bookmakers as a benchmark. We turned their [odds into probabilities](https://medium.com/geekculture/how-to-compute-football-implied-probabilities-from-bookmakers-odds-bbb33ccf7c1d). Try to beat them!

## Practical skills
 - Coding in python
 - Dealing with heterogeneous and missing data
 - Dealing with imbalanced and noisy classes
 - Use advanced machine learning techniques  like sequence learning, neural networks (but not limited to)
 
## Acknowledgements

The data are provided by [Octosport](https://www.octosport.io/) and [Sportmonks](https://www.sportmonks.com/) 

Good luck!