Conformal Score Prediction in Figure Skating Competitions

Varvara  Kisel; Ilia Nouretdinov; Alex Gammerman

Conformal Score Prediction in Figure Skating Competitions

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Predicting figure-skating scores is a challenging modelling problem because the International Skating Union (ISU) scoring system combines objective, rule-based evaluation of technical elements with subjective human judgement of artistic and performance quality. This study examines whether the final score of a skater can be estimated using only technical-element data, combining reliability (validity) and information (precision) of the prediction intervals produced by the Conformal Prediction framework for regression. In general, the results indicate that machine learning models can effectively learn scoring patterns in figure skating.

Original language	English
Title of host publication	Proceedings of Machine Learning Research
Subtitle of host publication	Fifteenth Symposium on Conformal and Probabilistic Prediction with Applications, 2-4 September 2026, Mölnlycke Health Care, Mölndal, Sweden
Pages	1076-1077
Number of pages	2
Volume	329
Publication status	Published - 4 Sept 2026

Access to Document

https://raw.githubusercontent.com/mlresearch/v329/main/assets/kisel26a/kisel26a.pdf

Cite this

Kisel, V., Nouretdinov, I., & Gammerman, A. (2026). Conformal Score Prediction in Figure Skating Competitions. In Proceedings of Machine Learning Research: Fifteenth Symposium on Conformal and Probabilistic Prediction with Applications, 2-4 September 2026, Mölnlycke Health Care, Mölndal, Sweden (Vol. 329, pp. 1076-1077) https://raw.githubusercontent.com/mlresearch/v329/main/assets/kisel26a/kisel26a.pdf

@inproceedings{e8d737221bbd444e80e4db1830a75405,

title = "Conformal Score Prediction in Figure Skating Competitions",

abstract = "Predicting figure-skating scores is a challenging modelling problem because the International Skating Union (ISU) scoring system combines objective, rule-based evaluation of technical elements with subjective human judgement of artistic and performance quality. This study examines whether the final score of a skater can be estimated using only technical-element data, combining reliability (validity) and information (precision) of the prediction intervals produced by the Conformal Prediction framework for regression. In general, the results indicate that machine learning models can effectively learn scoring patterns in figure skating.",

author = "Varvara Kisel and Ilia Nouretdinov and Alex Gammerman",

year = "2026",

month = sep,

day = "4",

language = "English",

volume = "329",

pages = "1076--1077",

booktitle = "Proceedings of Machine Learning Research",

}

Kisel, V, Nouretdinov, I & Gammerman, A 2026, Conformal Score Prediction in Figure Skating Competitions. in Proceedings of Machine Learning Research: Fifteenth Symposium on Conformal and Probabilistic Prediction with Applications, 2-4 September 2026, Mölnlycke Health Care, Mölndal, Sweden. vol. 329, pp. 1076-1077. <https://raw.githubusercontent.com/mlresearch/v329/main/assets/kisel26a/kisel26a.pdf>

Conformal Score Prediction in Figure Skating Competitions. / Kisel, Varvara ; Nouretdinov, Ilia ; Gammerman, Alex.
Proceedings of Machine Learning Research: Fifteenth Symposium on Conformal and Probabilistic Prediction with Applications, 2-4 September 2026, Mölnlycke Health Care, Mölndal, Sweden. Vol. 329 2026. p. 1076-1077.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Conformal Score Prediction in Figure Skating Competitions

AU - Kisel, Varvara

AU - Nouretdinov, Ilia

AU - Gammerman, Alex

PY - 2026/9/4

Y1 - 2026/9/4

N2 - Predicting figure-skating scores is a challenging modelling problem because the International Skating Union (ISU) scoring system combines objective, rule-based evaluation of technical elements with subjective human judgement of artistic and performance quality. This study examines whether the final score of a skater can be estimated using only technical-element data, combining reliability (validity) and information (precision) of the prediction intervals produced by the Conformal Prediction framework for regression. In general, the results indicate that machine learning models can effectively learn scoring patterns in figure skating.

AB - Predicting figure-skating scores is a challenging modelling problem because the International Skating Union (ISU) scoring system combines objective, rule-based evaluation of technical elements with subjective human judgement of artistic and performance quality. This study examines whether the final score of a skater can be estimated using only technical-element data, combining reliability (validity) and information (precision) of the prediction intervals produced by the Conformal Prediction framework for regression. In general, the results indicate that machine learning models can effectively learn scoring patterns in figure skating.

M3 - Conference contribution

VL - 329

SP - 1076

EP - 1077

BT - Proceedings of Machine Learning Research

ER -