As an avid sports enthusiast, I am passionate about football and how I can solve problems in football through computing. In this project, I propose to create a predictive model that can determine when a football player is likely to reach their peak performance. Understanding when a player will reach this phase in their career can significantly impact a manager/coach's decisions, contract negotiations, and overall team success.

Given the recent tightening of the enforcement of Financial Fair Play rules around Europe as can be seen with various points deductions that have been handed out to teams in the 2023/24 season, it is now more important than ever for teams to make the most of their budgets. One way they can do this is to make informed decisions when deciding on contracts for new and existing players. Being able to predict where a player is in terms of their career arc/potential is a vital piece of data that clubs need to use in contract negotiations and when building a team.

I propose to build a model that will attempt to determine when a player will reach peak performance. I will do this by collecting vast amounts of historical player data through APIs and publicly available datasets. I will take into account which statistics are key performance indicators for players in different positions. Furthermore, I will consider injuries, including the type of injury, the likelihood of reoccurrence and the subsequent effect specific injuries have on performance after they are suffered.

To achieve this, I will build a predictive model and use machine learning techniques, specifically regression. I will also use Python and its available libraries such as Scikit-learn. I will split the data I have collected and use the majority to train the model on the historical data. After this, I will use the remaining data to test and analyse the accuracy of the model I have built.