An xG Based Football Scouting System Using Machine Learning Techniques

In today's football landscape, scouting has evolved into a critical component for teams seeking hidden gems, established stars, and future talents. Amid this evolution, an innovative xG-based scouting system is poised to become a prominent fixture in the football lexicon. This system leverages the power of underlying stats like Expected Goals (xG) to meticulously evaluate players worldwide, recommending those who align with a team's unique needs and exhibit a significant potential.Our approach uses a combination of various regression models and geometric distances to combine a large range of metrics and staggering statistics to function as a talent scout, ushering in a new era of player identification. It is able to identify players with huge potential and recommend them to clubs using it. This paper provides a comprehensive insight into the working of our pioneering xG-based scouting system, detailing its data-driven recommendations for teams. Ultimately this xG based scouting system enhances a team's ability to unearth the stars of tomorrow.