STOCHASTIC PROCESSES AND MARKOV CHAIN PREDICTION MODEL FOR ICE HOCKEYPLAYER POSITION DATA
Far East Journal of Mathematical Sciences (FJMS) · 27.06.2026 · 143 (8) · 2479-2489
DOI: 10.17654/0972087126141 ↗Kurz gefasst
Fachartikel in der Zeitschrift Far East Journal of Mathematical Sciences (FJMS), online erschienen am 27.06.2026. Verfasst von Lin Wu. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This paper takes ice hockey player position data as the research object and constructs an improved Markov chain position prediction model based on stochastic process theory. An improved criterion and piecewise linear interpolation are used for data preprocessing. The ice rink is divided into three discrete states: offensive zone, neutral zone, and defensive zone. The state transition probability matrix is corrected by time weighting, Laplace smoothing coefficient, and state dwell weighting to achieve short-term player position prediction. Empirical results based on real player-tracking data show that the corrected transition probability distribution is more balanced. The overall prediction accuracy of the model is 74.5%, with an average error of 0.56. The error distribution is concentrated and stable, effectively characterizing the stochastic laws of position changes, providing quantitative support and practical methods for ice hockey tactical formulation and training optimization.
Zitieren
APA
Wu, L. (2026). STOCHASTIC PROCESSES AND MARKOV CHAIN PREDICTION MODEL FOR ICE HOCKEYPLAYER POSITION DATA. Far East Journal of Mathematical Sciences (FJMS), 143(8), 2479-2489. https://doi.org/10.17654/0972087126141
Vancouver
Wu L. STOCHASTIC PROCESSES AND MARKOV CHAIN PREDICTION MODEL FOR ICE HOCKEYPLAYER POSITION DATA. Far East Journal of Mathematical Sciences (FJMS). 2026;143(8):2479-2489. doi:10.17654/0972087126141
BibTeX
@article{Wu2026,
author = {Wu, Lin},
title = {STOCHASTIC PROCESSES AND MARKOV CHAIN PREDICTION MODEL FOR ICE HOCKEYPLAYER POSITION DATA},
journal = {Far East Journal of Mathematical Sciences (FJMS)},
year = {2026},
volume = {143},
number = {8},
pages = {2479--2489},
doi = {10.17654/0972087126141}
}
EUVIMED