Sign in to use this feature.

Years

Between: -

Subjects

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Journals

remove_circle_outline

Article Types

Countries / Regions

remove_circle_outline

Search Results (1)

Search Parameters:
Keywords = soccer player salaries

Order results
Result details
Results per page
Select all
Export citation of selected articles as:
20 pages, 2036 KB  
Article
Predicting Soccer Player Salaries with Both Traditional and Automated Machine Learning Approaches
by Davronbek Malikov, Pilsu Jung and Jaeho Kim
Appl. Sci. 2025, 15(14), 8108; https://doi.org/10.3390/app15148108 - 21 Jul 2025
Viewed by 505
Abstract
Soccer’s global popularity as the world’s favorite sport is driven by many factors, with high player salaries being one of the key reasons behind its appeal. These salaries not only reflect on-field performance, but also capture a broader evaluation of player value. Despite [...] Read more.
Soccer’s global popularity as the world’s favorite sport is driven by many factors, with high player salaries being one of the key reasons behind its appeal. These salaries not only reflect on-field performance, but also capture a broader evaluation of player value. Despite the increasing use of performance data in sports analytics, a critical gap remains in establishing fair compensation models that comprehensively account for both quantifiable and intangible contributions. To address these challenges, this study adopts machine learning (ML) techniques that model player salaries based on a combination of performance metrics and contextual features. This research focuses on reducing bias and improving transparency in salary decisions through a systematic, data-driven approach. Utilizing a dataset spanning the 2016–2022 seasons, we apply both traditional and automated ML frameworks to uncover the most influential factors in salary determination. The results indicate a nearly 17% improvement in R2 and about a 30% reduction in MAE after incorporating the newly constructed features and methods, demonstrating a significant enhancement in model performance. Gradient Boosting demonstrates superior effectiveness, revealing a group of significantly underestimated and overestimated players, and showcasing the model’s proficiency in detecting valuation discrepancies. Full article
Show Figures

Figure 1

Back to TopTop