Sports have become much more than just the game itself. It has widened its scope to brand building, entertainment, widening followers as well as developing players at grass-root level. Association football player wages and their release clause values have skyrocketed in the last decade. Teams all over the world and especially in Europe are willing to over lucrative deals for global star athletes. At the same time, they scout for potential superstars worldwide and try to lure them join the club at an early age. Therefore, it is extremely important for management to optimize their resources without compromising quality.
One of the key factor is deciding player wages. If there is a Ronaldo or Messi in your team and you fail to meet their expectations, there are at least 10 other clubs who are well equipped and prepared to take them away. On the other hand, if they are provided a much higher number, you might end up upsetting some other players and they could end up leaving the club. Also, the players will also understand the important factors that they need to improve to reach the top level. In this notebook, I will analyze the FIFA 18 dataset available at kaggle. The analysis will contain following factors:
- Data cleaning
- Data preparation
- Exploratory data analysis
- Predictive modeling
- Conclusion
The dataset will be divided into 4 sections based on the playing positions. They will be goalkeepers, defenders, midfielders and attackers. For each of these positions, the most important feature in deciding player wages will be determined.
Note: The wages mentioned and predicted are all on a weekly level
Download the entire fifa-player-wage-analysis folder to your local machine to access the project.
- Soumya Halder
- The Fifa 18 dataset from kaggle - https://www.kaggle.com/thec03u5/fifa-18-demo-player-dataset
- Data cleaning
- Data preparation
- Exploratory Data Analysis
- Predictive Modeling (Regression Analysis)
- Summary & Recommendations