Evaluating one-shot tournament predictions

Research output: Journal contributionsJournal articlesResearchpeer-review

Standard

Evaluating one-shot tournament predictions. / Ekstrom, Claus Thorn; Van Eetvelde, Hans; Ley, Christophe et al.
In: Journal of Sports Analytics, Vol. 7, No. 1, 05.04.2021, p. 37-46.

Research output: Journal contributionsJournal articlesResearchpeer-review

Harvard

APA

Vancouver

Ekstrom CT, Van Eetvelde H, Ley C, Brefeld U. Evaluating one-shot tournament predictions. Journal of Sports Analytics. 2021 Apr 5;7(1):37-46. doi: 10.3233/JSA-200454

Bibtex

@article{6a7afcb3403c4540b863a6f7c3298d1d,
title = "Evaluating one-shot tournament predictions",
abstract = "We introduce the Tournament Rank Probability Score (TRPS) as a measure to evaluate and compare pre-tournament predictions, where predictions of the full tournament results are required to be available before the tournament begins. The TRPS handles partial ranking of teams, gives credit to predictions that are only slightly wrong, and can be modified with weights to stress the importance of particular features of the tournament prediction. Thus, the Tournament Rank Prediction Score is more flexible than the commonly preferred log loss score for such tasks. In addition, we show how predictions from historic tournaments can be optimally combined into ensemble predictions in order to maximize the TRPS for a new tournament.",
keywords = "Tournament prediction, rank probability score, sport prediction, ensemble predictions, Informatics, Business informatics",
author = "Ekstrom, {Claus Thorn} and {Van Eetvelde}, Hans and Christophe Ley and Ulf Brefeld",
year = "2021",
month = apr,
day = "5",
doi = "10.3233/JSA-200454",
language = "English",
volume = "7",
pages = "37--46",
journal = "Journal of Sports Analytics",
issn = "2215-020X",
publisher = "IOS Press BV",
number = "1",

}

RIS

TY - JOUR

T1 - Evaluating one-shot tournament predictions

AU - Ekstrom, Claus Thorn

AU - Van Eetvelde, Hans

AU - Ley, Christophe

AU - Brefeld, Ulf

PY - 2021/4/5

Y1 - 2021/4/5

N2 - We introduce the Tournament Rank Probability Score (TRPS) as a measure to evaluate and compare pre-tournament predictions, where predictions of the full tournament results are required to be available before the tournament begins. The TRPS handles partial ranking of teams, gives credit to predictions that are only slightly wrong, and can be modified with weights to stress the importance of particular features of the tournament prediction. Thus, the Tournament Rank Prediction Score is more flexible than the commonly preferred log loss score for such tasks. In addition, we show how predictions from historic tournaments can be optimally combined into ensemble predictions in order to maximize the TRPS for a new tournament.

AB - We introduce the Tournament Rank Probability Score (TRPS) as a measure to evaluate and compare pre-tournament predictions, where predictions of the full tournament results are required to be available before the tournament begins. The TRPS handles partial ranking of teams, gives credit to predictions that are only slightly wrong, and can be modified with weights to stress the importance of particular features of the tournament prediction. Thus, the Tournament Rank Prediction Score is more flexible than the commonly preferred log loss score for such tasks. In addition, we show how predictions from historic tournaments can be optimally combined into ensemble predictions in order to maximize the TRPS for a new tournament.

KW - Tournament prediction

KW - rank probability score

KW - sport prediction

KW - ensemble predictions

KW - Informatics

KW - Business informatics

UR - https://www.mendeley.com/catalogue/3cfdf972-c343-3391-b884-8f631a241695/

U2 - 10.3233/JSA-200454

DO - 10.3233/JSA-200454

M3 - Journal articles

VL - 7

SP - 37

EP - 46

JO - Journal of Sports Analytics

JF - Journal of Sports Analytics

SN - 2215-020X

IS - 1

ER -

Documents

DOI