ANALYSIS OF FOOTBALL TRANSFERS IN EUROPE USING NETWORK SCIENCE Jan 2016 – Apr 2016 Project description Football is arguably the most popular game worldwide, and from a network perspective it provides myriad of data to analyse. Association Football in Europe is the hub for all the businesses related to the game as well as dream destinations of many players across the globe. The movement of a player from one club to another is termed a football transfer and this event has a fee involved between the dealing clubs, most of the time. Since such transfers make or break a club’s performance for a season or more, they are a subject of immense interest in sports analytics and football betting. Using network science techniques, we analyze the European transfer market from data for 6 seasons spanning the top 5 countries playing football. We learn how this directed network of multiple attributes and dimensions can unravel and confirm some club performances based on network characteristics like betweenness centrality, reciprocity, and transitivity. The data is collected using Python and all social network analysis is performed using R.
ANALYSIS OF FOOTBALL TRANSFERS IN EUROPE USING NETWORK SCIENCE Jan 2016 – Apr 2016 Project description Football is arguably the most popular game worldwide, and from a network perspective it provides myriad of data to analyse. Association Football in Europe is the hub for all the businesses related to the game as well as dream destinations of many players across the globe. The movement of a player from one club to another is termed a football transfer and this event has a fee involved between the dealing clubs, most of the time. Since such transfers make or break a club’s performance for a season or more, they are a subject of immense interest in sports analytics and football betting. Using network science techniques, we analyze the European transfer market from data for 6 seasons spanning the top 5 countries playing football. We learn how this directed network of multiple attributes and dimensions can unravel and confirm some club performances based on network characteristics like betweenness centrality, reciprocity, and transitivity. The data is collected using Python and all social network analysis is performed using R.