2026-09-20T08:57:19Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1392052022-01-15T04:04:18Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Hosoi, Anette “Peko”
Jutamulia, Ivan C.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2022-01-14T14:56:34Z
2022-01-14T14:56:34Z
2021-06
2021-06-17T20:13:26.142Z
https://hdl.handle.net/1721.1/139205
Quantifying decision-making in professional basketball has been an extremely challenging area of research in the past decade, with potentially very fruitful and powerful insights to be drawn as NBA organizations want to understand cognitive aspects of athlete performance. This work seeks to develop an objective framework for evaluating decision-making, while simultaneously making inferences around strategy and execution efficacy.
I construct a metric called Expected Possession Value (EPV) computed through tracking data that is then leveraged to identify scoring opportunities throughout a game. I then analyze these opportunities as instances of decision-making, quantifying how often those opportunities are missed and how good those opportunities were. Looking at team opportunities as a whole and relying on the notion of expectation, I am then also able to make judgements on how much of a team’s performance can be attributed to their strategy versus their execution. Through this analysis, I show that using EPV is an effective framework for extracting quantitative measures to aid in decision-making evaluation through tracking data.
M.Eng.
Massachusetts Institute of Technology
In Copyright - Educational Use Permitted
Copyright MIT
http://rightsstatements.org/page/InC-EDU/1.0/
Expected Possession Value: An Evaluation Framework for Decision-Making, Strategy, and Execution in Basketball
Thesis
application/pdf
Master
Master of Engineering in Electrical Engineering and Computer Science
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="1a99c538-68d6-483a-9a91-ea608449975e">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Title>Expected Possession Value: An Evaluation Framework for Decision-Making, Strategy, and Execution in Basketball</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2021-06</PublicationDate>
<Authors>
<Author>
<DisplayName>Jutamulia, Ivan C.</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>http://rightsstatements.org/page/InC-EDU/1.0/</License>
<Abstract>Quantifying decision-making in professional basketball has been an extremely challenging area of research in the past decade, with potentially very fruitful and powerful insights to be drawn as NBA organizations want to understand cognitive aspects of athlete performance. This work seeks to develop an objective framework for evaluating decision-making, while simultaneously making inferences around strategy and execution efficacy.
I construct a metric called Expected Possession Value (EPV) computed through tracking data that is then leveraged to identify scoring opportunities throughout a game. I then analyze these opportunities as instances of decision-making, quantifying how often those opportunities are missed and how good those opportunities were. Looking at team opportunities as a whole and relying on the notion of expectation, I am then also able to make judgements on how much of a team’s performance can be attributed to their strategy versus their execution. Through this analysis, I show that using EPV is an effective framework for extracting quantitative measures to aid in decision-making evaluation through tracking data.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>