Football, like the rest of the world, is constantly changing. As new techniques for data analysis and model construction continue to emerge the sport is increasingly embracing a data-driven approach, adapting to the ever-changing landscape of information and analytics.One part of the data-driven approach football have been adapting is to use machine learning to assist in player valuation. In a world where money is being pumped in from rich oligarchs and sheiks and player prices are steadily rising, clubs need to be able to locate the right players for the right prices and data analytics might help with that.

The purpose of this project is to collect data and statistics related to transfers and players over the past eight years. Through the utilization of three different machine learning techniques and analyzing the gathered data, the aim is to identify the most effective method for player valuation, thereby enhancing the accuracy of the assessment process.

During the project 14216 transfers from all over the world were gathered, featured engineered and used in the different machine learning techniques to predict player transfer costs. Evaluation metrics for the models were calculated and importance of the features are discussed.The machine learning algorithms for the project were able to predict the transfer fees of football player with a high R-squared value which indicates the proportion of the variance in the transfer fees of football players can be explained by the model's predictions