Evaluating NBA end-of-game decision-making

McFarlane, Patrick

doi:10.3233/jsa-180231

Cited by 7 publications

(10 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Huyghe also pointed out that for a better understanding of the NBA game baseline approach and how it needs to be played, it's indeed crucial to be familiar with the components of the NBA basketball court [8]. Even though it's not as crucial for spectators, it might be helpful to understand whenever people refer to the lane, the paint, the ten-second line, or the baseline [8,10]. Such terminologies and court features are essential to understanding the NBA game of Basketball and how it has been performed.…”

Section: Stadium and Baseline Methodsmentioning

confidence: 99%

“…While always watching these activities on television, the experience of the games has changed. The vitality and improvisation of a high-pressure game together in a packed stadium seem to have been absent from the NBA for a while [10]. What with last year's playoffs currently happening in a crowd-less bubble at Disney World and the majority of the 2020-21 season opener in arenas that occurred empty or massively diminished in volume?…”

Section: Issues Linked With Host Spacesmentioning

confidence: 99%

See 1 more Smart Citation

Research on the Development Mode Status Analysis and Optimization Strategy of the NBA

Bai¹

2022

HBEM

View full text Add to dashboard Cite

In 1949, the National Basketball League became the National Basketball Association (NBL). The league’s corporate offices, located at 645 Fifth Avenue in New York City’s Olympic Tower, serve as the base of operations for its numerous corporate executives. The All-Star Game, an amateur basketball competition held in February by the National Basketball Association, features 24 of the best players in the league. It is the main event of the three-day NBA All-Star Week, which runs from Friday to Sunday. However, what makes these athletes practice so much? In essence, Basketball is both livelihood & occupation of choice for such athletes. These players enjoy playing the game but are well compensated for their labor. They must also practice daily to keep great basketball talents at a high level if players want to maintain their NBA professions successfully. The research on the NBA’s development mode status analysis and optimization approach is explained in detail in this paper.

show abstract

Section: Stadium and Baseline Methodsmentioning

confidence: 99%

Section: Issues Linked With Host Spacesmentioning

confidence: 99%

Research on the Development Mode Status Analysis and Optimization Strategy of the NBA

Bai¹

2022

HBEM

View full text Add to dashboard Cite

show abstract

“…Recent work has also explored mechanisms that facilitate the analysis of the decisions players and coaches make in a given match (Kaya 2014;Bar-Eli and Tractinsky 2000). Some have tried to analyze the efficiency and optimality of decisions across the game (Goldman and Rao 2011;Wang et al 2018), while others have focused on the decisions made in the final minutes of the game, when they are most critical (McFarlane 2018). Also, attempts were made to model strategic in-game interactions in order to simulate and analyze counterfactual scenarios (Sandholtz and Bornn 2018) and to understand the interplay in dynamic space creation between offense and defense (Lamas et al 2015).…”

Section: Prediction and Analysis In Basketballmentioning

confidence: 99%

Predicting In-game Actions from Interviews of NBA Players

Oved

Feder

Reichart

2019

Preprint

View full text Add to dashboard Cite

Sports competitions are widely researched in computer and social science, with the goal of understanding how players act under uncertainty. While there is an abundance of computational work on player metrics prediction based on past performance, very few attempts to incorporate out-ofgame signals have been made. Specifically, it was previously unclear whether linguistic signals gathered from players' interviews can add information which does not appear in performance metrics. To bridge that gap, we define text classification tasks of predicting deviations from mean in NBA players' in-game actions, which are associated with strategic choices, player behavior and risk, using their choice of language prior to the game. We collected a dataset of transcripts from key NBA players' pre-game interviews and their in-game performance metrics, totalling in 5,226 interview-metric pairs. We design neural models for players' action prediction based on increasingly more complex aspects of the language signals in their open-ended interviews. Our models can make their predictions based on the textual signal alone, or on a combination of that signal with signals from past-performance metrics. Our text-based models outperform strong baselines trained on performance metrics only, demonstrating the importance of language usage for action prediction. Moreover, the models that employ both textual input and pastperformance metrics produced the best results. Finally, as neural networks are notoriously difficult to interpret, we propose a method for gaining further insight into what our models have learned. Particularly, we present an LDA-based analysis, where we interpret model predictions in terms of correlated topics. We find that our best performing textual model is most associated with topics that are intuitively related to each prediction task and that better models yield higher correlation with more informative topics. 1

show abstract

“…There has been little research in the field of predictive sports game outcome. One notable exception is McFarlane's [22] paper on predicting the outcome of Basketball games. But it is limited to only the last 3 minutes of the game.…”

Section: Game Outcome Researchmentioning

confidence: 99%

Predictive Models for Game Outcomes in Women's Lacrosse

Brown¹

2019

MathSJ

View full text Add to dashboard Cite

This research presents a predictive model for determining the game outcome of a Women's (Female) Lacrosse game. This is important to coaches regardless of if their team appears to be winning or losing the game. Coaches make decisions throughout the game based upon the belief that they are winning or losing. The model is a Logistic Regression model and can be used with very little data from a game: time remaining and difference between the scores. This could be a valuable tool to coaches that can be used during the game. It is more than 89% accurate. Data used in this research comes from direct matchup games between BigTen Women's Lacrosse teams. The win probability equations, including coefficients, are presented.

show abstract

Evaluating NBA end-of-game decision-making

Cited by 7 publications

References 1 publication

Research on the Development Mode Status Analysis and Optimization Strategy of the NBA

Research on the Development Mode Status Analysis and Optimization Strategy of the NBA

Predicting In-game Actions from Interviews of NBA Players

Predictive Models for Game Outcomes in Women's Lacrosse

Contact Info

Product

Resources

About