Тёмный

Valuing actions intro: The principles of valuing actions 

Friends of Tracking
Подписаться 23 тыс.
Просмотров 6 тыс.
50% 1

Lotte Bransen gives an introduction to a series of lectures on valuing actions in football using statistical models and machine learning.
Contents:
- Why go beyond traditional statistics to assess football players?
- How to assess the performances of football players?
- What does the VAEP framework have to offer?
- What will you learn in upcoming tutorials?
All the code for this tutorial series is available here: github.com/Sci...
References:
Sarah Rudd. A Framework for Tactical Analysis and Individual Offensive Production Assessment in Soccer Using Markov Chains. nessis.org/ness...
Karun Singh. Introducing expected threat. karun.in/blog/....
Javier Fernández, Luke Bornn, Dan Cervone. Decomposing the Immeasurable Sport: A deep learning expected possession value framework for soccer. MIT Sloan Sports Analytics, 2019.
Maaike Van Roy, Pieter Robberechts, Tom Decroos, Jesse Davis. Valuing On-the-Ball Actions in Soccer: A Critical Comparison of xT and VAEP. AAAI 2020 Workshop on Artificial Intelligence in Team Sports, 2020.
Derrick Yam. Attacking Contributions: Markov Models for Football. statsbomb.com/...
Nils Mackay. BLOG: Introducing a Possession Value framework. www.optasports...
Aditya Kothari. xPo. thecomeonman.g...
John Muller. Goals added: introducing a new way to measure soccer. www.americanso...

Опубликовано:

 

12 сен 2024

Поделиться:

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист
Посмотреть позже
Комментарии : 8   
@mr.heuhoi1446
@mr.heuhoi1446 4 года назад
Thank you for providing such in depth knowledge for free and in such a structured way! Enjoying every video!
@hrantbaloyan4652
@hrantbaloyan4652 4 года назад
Really thank you for doing such things for free.
@mattwasserberg8489
@mattwasserberg8489 4 года назад
This is a really great introduction. Thanks very much, Lotte.
@mattiaarsendi5421
@mattiaarsendi5421 4 года назад
Really thank you for this great material !
@mranonymous8815
@mranonymous8815 3 года назад
Hello, thanks for the interesting talk. In the slide from 10:38 you describe nearest neighbor methods (like for example SVMs or Kernel density estimators would be), but in the corresponding paper (KDD2019) in the Appendix Logistic Regression and Gradient Tree Boosting methods are given as being applied in the experiments, which aren't nearest neighbor methods. Could you please explain where my misunderstanding comes from?
@dunghuynh2460
@dunghuynh2460 3 года назад
Please check for the email, Mr. David Sumpter
@Frazzawolt
@Frazzawolt 4 года назад
soccer*
@AmitKumar-wz4wb
@AmitKumar-wz4wb 3 года назад
Football**
Далее
How to Build An Expected Goals Model 1: Data and Model
23:05
Faites comme moi
00:14
Просмотров 1,3 млн
Мужа или парня
00:42
Просмотров 14 тыс.
ФОКУС -СВЕТОФОР
00:32
Просмотров 267 тыс.
Declining Value of Papers in Academia
21:59
Просмотров 328 тыс.
The Ultimate Guide to Expected Goals
46:31
Просмотров 17 тыс.
Plus-minus ratings vs. VAEP
11:55
Просмотров 354
Why you should not be a data scientist
12:33
Просмотров 761 тыс.
Faites comme moi
00:14
Просмотров 1,3 млн