東華大學圖書館 |

An Approximate Dynamic Programming Approach to Determine the Optimal Draft Strategy for a Single Team During the National Football League Draft.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	An Approximate Dynamic Programming Approach to Determine the Optimal Draft Strategy for a Single Team During the National Football League Draft./
作者:	Crofford, Ira L., Jr.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
面頁冊數:	140 p.
附註:	Source: Dissertations Abstracts International, Volume: 83-03, Section: B.
Contained By:	Dissertations Abstracts International83-03B.
標題:	Operations research. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28417697
ISBN:	9798535568522

An Approximate Dynamic Programming Approach to Determine the Optimal Draft Strategy for a Single Team During the National Football League Draft.
Crofford, Ira L., Jr.

An Approximate Dynamic Programming Approach to Determine the Optimal Draft Strategy for a Single Team During the National Football League Draft. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 140 p.

Source: Dissertations Abstracts International, Volume: 83-03, Section: B.

Thesis (Ph.D.)--George Mason University, 2021.

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

The purpose of this research is to determine the optimal strategy for a single team when participating in the National Football League (NFL) Draft using Approximate Dynamic Programming (ADP). General managers and coaches currently draft the best player available (BPA), a player that fills a certain positional need, or a hybrid of the two. Also, general managers must make sequential decisions in terms of trading up to go for a specific player while sacrificing future draft capital or possibly trading back and gaining more future draft capital. If done correctly, teams hope to still get their specific player, but for the right cost in terms of when the player gets drafted. In other words, a team wants to draft a player when he should have been drafted according to his skill set, not much earlier. This research attempts to answer when a team should trade up, when a team should trade back, when they should draft for team needs, or when they should take the BPA. Many jobs and careers are riding on the success of a football team. Nothing can turn around the prosperity of a franchise like a successful weekend at the NFL Draft. At the same time, an unsuccessful weekend can result in multiple years of disappointment and setbacks, not to mention the effects monetarily on the ownership of the team. Sometimes teams spend too much draft capital to move into position for a player that never materializes into the player they had hoped. There are many ways for a team to fail during the draft. However, most of the tools used to predict the draft or to have a successful draft are not tailored for an actual draft. There are many tools to assist a fan of the game of football to conduct a fantasy football draft. There are even tools to assist a fan with preparing for whom his team should draft, but even these projected drafts are just the best guesses of an "expert" from outside of the organizations (teams).This research investigates how a team should maneuver themselves during the NFL Draft to draft the best-graded team possible (on paper) using ADP. This research provides insight as to what the best strategy is for a team trying to create the optimal team roster given their current roster and the list of draft-eligible players.The results indicate that the ADP Hybrid Strategy was better than the pure BPA Strategy in the long-term. This research is, not only expected to contribute to the NFL Community with the application of ADP to help project the NFL Draft, but also to many different organizations who are trying to better themselves. The teams are competing for scarce resources and they must be able to see themselves (their strengths and weaknesses), as well as that of their opponents or competitors.The uncertainty of the competitors' actions and the uncertainty of the real potential of the resources takes this to a whole new level. One such organization could be the United States (U.S.) Army Human Resources Command who could employ a similar methodology to better assign Second Lieutenants to different branches of the U.S. Army to ensure that all teams (branches in this case) are improved and that the league (U.S. Army) is also improved.

ISBN: 9798535568522Subjects--Topical Terms:

547123
Operations research.
Subjects--Index Terms:

Approximate dynamic programming

An Approximate Dynamic Programming Approach to Determine the Optimal Draft Strategy for a Single Team During the National Football League Draft.
LDR:04478nmm a2200397 4500 001 2351869
005 20221111113701.5
008 241004s2021 ||||||||||||||||| ||eng d
020 $a 9798535568522
035 $a (MiAaPQ)AAI28417697
035 $a AAI28417697
040 $a MiAaPQ $c MiAaPQ
100 1 $a Crofford, Ira L., Jr. $0 (orcid)0000-0002-2761-7516 $3 3691453
245 1 3 $a An Approximate Dynamic Programming Approach to Determine the Optimal Draft Strategy for a Single Team During the National Football League Draft.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 140 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-03, Section: B.
500 $a Advisor: Ganesan, Rajesh.
502 $a Thesis (Ph.D.)--George Mason University, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a The purpose of this research is to determine the optimal strategy for a single team when participating in the National Football League (NFL) Draft using Approximate Dynamic Programming (ADP). General managers and coaches currently draft the best player available (BPA), a player that fills a certain positional need, or a hybrid of the two. Also, general managers must make sequential decisions in terms of trading up to go for a specific player while sacrificing future draft capital or possibly trading back and gaining more future draft capital. If done correctly, teams hope to still get their specific player, but for the right cost in terms of when the player gets drafted. In other words, a team wants to draft a player when he should have been drafted according to his skill set, not much earlier. This research attempts to answer when a team should trade up, when a team should trade back, when they should draft for team needs, or when they should take the BPA. Many jobs and careers are riding on the success of a football team. Nothing can turn around the prosperity of a franchise like a successful weekend at the NFL Draft. At the same time, an unsuccessful weekend can result in multiple years of disappointment and setbacks, not to mention the effects monetarily on the ownership of the team. Sometimes teams spend too much draft capital to move into position for a player that never materializes into the player they had hoped. There are many ways for a team to fail during the draft. However, most of the tools used to predict the draft or to have a successful draft are not tailored for an actual draft. There are many tools to assist a fan of the game of football to conduct a fantasy football draft. There are even tools to assist a fan with preparing for whom his team should draft, but even these projected drafts are just the best guesses of an "expert" from outside of the organizations (teams).This research investigates how a team should maneuver themselves during the NFL Draft to draft the best-graded team possible (on paper) using ADP. This research provides insight as to what the best strategy is for a team trying to create the optimal team roster given their current roster and the list of draft-eligible players.The results indicate that the ADP Hybrid Strategy was better than the pure BPA Strategy in the long-term. This research is, not only expected to contribute to the NFL Community with the application of ADP to help project the NFL Draft, but also to many different organizations who are trying to better themselves. The teams are competing for scarce resources and they must be able to see themselves (their strengths and weaknesses), as well as that of their opponents or competitors.The uncertainty of the competitors' actions and the uncertainty of the real potential of the resources takes this to a whole new level. One such organization could be the United States (U.S.) Army Human Resources Command who could employ a similar methodology to better assign Second Lieutenants to different branches of the U.S. Army to ensure that all teams (branches in this case) are improved and that the league (U.S. Army) is also improved.
590 $a School code: 0883.
650 4 $a Operations research. $3 547123
650 4 $a Statistics. $3 517247
650 4 $a Computer engineering. $3 621879
650 4 $a Statistical physics. $3 536281
650 4 $a Sports management. $3 3423935
653 $a Approximate dynamic programming
653 $a Bayesian inference
653 $a National Football League
653 $a Reinforcement learning
653 $a Sports draft
690 $a 0796
690 $a 0463
690 $a 0464
690 $a 0217
690 $a 0430
710 2 $a George Mason University. $b Systems Engineering and Operations Research. $3 3682738
773 0 $t Dissertations Abstracts International $g 83-03B.
790 $a 0883
791 $a Ph.D.
792 $a 2021
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28417697