In this work we analyse the global soccer player transfer market providing a network approach that takes into account both the number of transfers and the related costs for football players in the world market. We propose a community detection methodology that considers different features of the network. We cluster countries according to similarities in their roles in the transfer market and to the presence of indirect connections due to common neighbours. Numerical results show a strict relation between the composition of clusters and the economic value of the football leagues of different countries. Indeed, we observe that, on average, leagues with a similar economic value belongs to the same cluster. The analysis has been also extended providing a comparison based on the world trade network. We observe that prominent European players in the economic trades are also relevant in the soccer transfer network.
|Rivista||Annals of Operations Research|
|Stato di pubblicazione||Pubblicato - 2022|
- Attributed networks
- Community detection
- Data science
- Economic trade