東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Markov Modeling in Sports Analytics.

Martin, Luis.

FindBook

Google Book

Amazon

博客來

Markov Modeling in Sports Analytics.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Markov Modeling in Sports Analytics./
作者:	Martin, Luis.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2020,
面頁冊數:	108 p.
附註:	Source: Dissertations Abstracts International, Volume: 83-02, Section: B.
Contained By:	Dissertations Abstracts International83-02B.
標題:	Sports management. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=27998997
ISBN:	9798535580043

Markov Modeling in Sports Analytics.
Martin, Luis.

Markov Modeling in Sports Analytics. - Ann Arbor : ProQuest Dissertations & Theses, 2020 - 108 p.

Source: Dissertations Abstracts International, Volume: 83-02, Section: B.

Thesis (D.B.A.)--St. Thomas University, 2020.

This item must not be sold to any third party vendors.

Sports analytics applies mathematical and statistical concepts to making relevant and efficient choices for proper club management in finances and performance in the field. This study models a technique to evaluate player performance based on games they have been involved with previously. The analysis is conducted considering all events in a match in which the player affected the progress of the ball to model the overall team rating as an aggregate for all players' ratings. The resultant functions estimate the winning probability of a team as used by betting and forecasting companies. The methodology applies Markov event chains to model the probabilities of transitions of the ball based on previous events. Statistically evaluated probabilities give reliable predictions of the game and reliability of each player in his or her assigned positions. The choice of Markov chains analysis is based on the model's dependence on the most recent data about the players including the first half of a game, instead of historical data, which may be biased. Further, Markov chains are sensitive to small changes in data, which makes this approach the best in handling the present research's problem statement. The study takes a quantitative approach with data obtained from Opta Sports' website, which is altered to fit the desired dataset for evaluation. All actions that trigger the movement of the ball are considered as events. Different models are used to compare the transition probabilities achieved after an observation of the events. The impacts of four primary events: Corner, Goal Kick, Free Kick, and Throw in are assessed using Logit regression. The results of the analysis depict a close relationship between data-driven rating from the Markov models and the performance of a player as predicted. The details are efficient when obtaining a substitute player and when predicting the expected performance of the team. The Markov chains model can be used in prediction of games based on an assessment of previous performances, determining the worth of a player, and in making financial decisions for the club affecting the players and arrangement of a team.

ISBN: 9798535580043Subjects--Topical Terms:

3423935
Sports management.
Subjects--Index Terms:

Markov

Markov Modeling in Sports Analytics.
LDR:03159nmm a2200325 4500 001 2283926
005 20211115071949.5
008 220723s2020 ||||||||||||||||| ||eng d
020 $a 9798535580043
035 $a (MiAaPQ)AAI27998997
035 $a AAI27998997
040 $a MiAaPQ $c MiAaPQ
100 1 $a Martin, Luis. $3 3563002
245 1 0 $a Markov Modeling in Sports Analytics.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2020
300 $a 108 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-02, Section: B.
500 $a Advisor: Abernethy, Ted.
502 $a Thesis (D.B.A.)--St. Thomas University, 2020.
506 $a This item must not be sold to any third party vendors.
520 $a Sports analytics applies mathematical and statistical concepts to making relevant and efficient choices for proper club management in finances and performance in the field. This study models a technique to evaluate player performance based on games they have been involved with previously. The analysis is conducted considering all events in a match in which the player affected the progress of the ball to model the overall team rating as an aggregate for all players' ratings. The resultant functions estimate the winning probability of a team as used by betting and forecasting companies. The methodology applies Markov event chains to model the probabilities of transitions of the ball based on previous events. Statistically evaluated probabilities give reliable predictions of the game and reliability of each player in his or her assigned positions. The choice of Markov chains analysis is based on the model's dependence on the most recent data about the players including the first half of a game, instead of historical data, which may be biased. Further, Markov chains are sensitive to small changes in data, which makes this approach the best in handling the present research's problem statement. The study takes a quantitative approach with data obtained from Opta Sports' website, which is altered to fit the desired dataset for evaluation. All actions that trigger the movement of the ball are considered as events. Different models are used to compare the transition probabilities achieved after an observation of the events. The impacts of four primary events: Corner, Goal Kick, Free Kick, and Throw in are assessed using Logit regression. The results of the analysis depict a close relationship between data-driven rating from the Markov models and the performance of a player as predicted. The details are efficient when obtaining a substitute player and when predicting the expected performance of the team. The Markov chains model can be used in prediction of games based on an assessment of previous performances, determining the worth of a player, and in making financial decisions for the club affecting the players and arrangement of a team.
590 $a School code: 0552.
650 4 $a Sports management. $3 3423935
650 4 $a Statistics. $3 517247
650 4 $a Research. $3 531893
650 4 $a Population. $3 518693
650 4 $a Accuracy. $3 3559958
650 4 $a Random variables. $3 646291
650 4 $a Athletic recruitment. $3 3556676
650 4 $a Gambling. $3 663711
650 4 $a Data analysis. $2 bisacsh $3 3515250
650 4 $a Coaches & managers. $3 3435335
650 4 $a Performance evaluation. $3 3562292
650 4 $a Expenditures. $3 3556049
650 4 $a Statistical analysis. $3 3543751
650 4 $a Professional soccer. $3 3563003
650 4 $a Decision making. $3 517204
650 4 $a Data collection. $3 3561708
650 4 $a Probability. $3 518898
650 4 $a Stochastic models. $3 764002
650 4 $a Algorithms. $3 536374
650 4 $a Ratings & rankings. $3 3562221
650 4 $a Soccer. $3 520214
650 4 $a Ordinary differential equations. $3 3563004
650 4 $a Markov analysis. $3 3562906
653 $a Markov
653 $a Club management
690 $a 0430
690 $a 0463
710 2 $a St. Thomas University. $b Sport Administration. $3 3541169
773 0 $t Dissertations Abstracts International $g 83-02B.
790 $a 0552
791 $a D.B.A.
792 $a 2020
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=27998997