<![CDATA[Football team management involves complex decision-making processes that require evaluating high-dimensional player attributes while accounting for positional roles and tactical structures. Modern football simulation environments, such as Football Manager, provide rich datasets suitable for exploring decision-support approaches to lineup selection and formation planning. This paper proposes a hierarchical role-based scoring framework for automated best XI selection and formation-based role assignment. The method organizes player attributes into role-specific groups and applies weighted aggregation to reflect positional relevance, producing interpretable role scores for eight football positions. The framework is evaluated using a full-season simulation on a real club dataset, comparing three lineup strategies: default AI tactics, mean-based attribute scoring, and the proposed hierarchical weighting approach. Results demonstrate that the weighted scoring framework achieves substantially improved league performance under the evaluated conditions, as reflected by higher points accumulation and improved goal difference compared to baseline methods. The findings highlight the importance of structured role modeling in football analytics and support the use of simulation-based environments as valid testbeds for decision-support systems. The proposed approach is intended to assist, rather than replace human managers, offering analytical recommendations that enhance tactical decision-making in football simulations and serious games.]]>
Copyrights © 2026
