Cross-era Soccer Player Evaluation System based on Adaptive Weighting and Honor Competition Scheduling

DOI: https://doi.org/10.62517/jbdc.202501308

Author(s)

Xingye Zhang

Affiliation(s)

Computer and Artificial Intelligence Departments, Shandong University Finance and Economy, Jinan, Shandong, China

Abstract

Under the background of big data-driven sports analysis paradigm transformation, the comprehensive evaluation of soccer players faces the double challenges of insufficient cross-position fairness and static evaluation of honor value. Due to the solidified position weight and the neglect of the honor competition intensity in the traditional scoring system, the quantitative imbalance of the value of different role players and the lack of cross-era evaluation benchmarks are caused. This study proposes a comprehensive scoring model with cross-position adaptive weighting and honor dynamic weighting. By constructing an evaluation framework including attack, defense, organization, tactical role, and honor dimensions, the dynamic weight optimization is realized by combining Analytic Hierarchy Process (AHP) and random forest algorithm to solve the fair comparison problem under position differences. The technical scheme of the whole process from multi-source data collection, feature engineering to dynamic scoring was designed, and the "Honor competition intensity factor (CFI)" was innovatively introduced to calibrate the honor value based on the intensity of competition and the strength distribution of candidates. The system function module planning covers data processing, model training and visual analysis, and is expected to be applied to professional club recruitment decision-making, player market valuation and mass sports data analysis scenarios. This study provides a methodology innovation that integrates domain knowledge and data-driven for the field of intelligent sports analysis, and lays a technical foundation for cross-era player evaluation.

Keywords

Football Player Evaluation; Multi-Dimensional Weighted Scoring; Cross-Location Comparison; Honor Weight Adjustment; Machine Learning; Intelligent Sports Analysis

References

[1] Stephan Wolf, Maximilian Schmitt, Björn Schuller (2021). A football player rating system. Journal of Sports Analytics 6 (4), 243-257, 2021. [2] Andres Chacoma (2025, February). Identification and Optimization of High-Performance Passing Networks in Football. arXiv preprint arXiv:2502.01444, 2025. [3] Luca Pappalardo, Paolo Cintia, Paolo Ferragina, Emanuele Massucco, Dino Pedreschi, Fosca Giannotti (2019). PlayeRank: data-driven performance evaluation and player ranking in soccer via a machine learning approach. ACM Transactions on Intelligent Systems and Technology (TIST) 10 (5), 1-27, 2019. [4] Fernández, J., & Bornn, L. (2018). Wide Open Spaces: A statistical technique for measuring space creation in professional soccer. Journal of Quantitative Analysis in Sports, 14(2), 71-80, 2018. [5] Dong Hee Jung, & Jason J Jung. (2025). Data-driven understanding on soccer team tactics and ranking trends: Elo rating-based trends on European soccer leagues. PloS one, 20(2), e0318485, 2025. [6] Routley, K., & Schulte, O. (2015). A Markov Game Model for Valuing Player Actions in Ice Hockey. Proceedings of the Thirty-First Conference on Uncertainty in Artificial Intelligence, 782-791, 2015. [7] Dai Zhiwei. Application of digital physical training in the training of adolescent football players [J]. Sports, Games and Technology, 2025, (14):89-91. [8] Peng Hongwei. Construction of a comprehensive quality evaluation model for junior high school football players driven by big data [J]. Sports, Culture and Technology, 2024(16):178-180.