Football is among the most widely followed sports globally, with professional clubs evolving into complex business entities, and within this context, match ticket pricing strategies play a crucial role in revenue optimization. This paper aims to develop and validate a data-driven framework for optimizing ticket pricing in professional football using ML techniques and advanced optimization models. The proposed framework consists of three phases: first, a survey incorporating choice-based conjoint analysis is administered to fans to assess their preferences regarding key match-related attributes. The resulting insights enable the construction of a tailored variable for predictive modeling. Second, Machine Learning models, trained on historical sales and match data, are employed to predict the likelihood of a specific stadium seat being sold at a given price. Finally, an optimization algorithm determines an optimal pricing strategy that maximizes revenue while preserving accessibility for fans. The framework was empirically validated in collaboration with a top-tier Italian football club during the 2023–24 season and the implementation of the proposed pricing strategy resulted in a substantial increase in ticket sales (+14%) and ticketing revenues (+39%) compared to the previous season, under equivalent external conditions. These findings demonstrate the potential of data-driven pricing strategies in enhancing revenue management in professional sports and provide valuable insights for both academics and industry practitioners.
Arboretti et al. (Tue,) studied this question.