NBA Games Research Articles

A Data Science and Sports Analytics Approach to Decode Clutch Dynamics in the Last Minutes of NBA Games

A Data Science and Sports Analytics Approach to Decode Clutch Dynamics in the Last Minutes of NBA Games

The Three-Point Revolution: A Profound Impact on NBA Game Strategy

The Three-Point Revolution: A Profound Impact on NBA Game Strategy

Research on momentum conversion in sports

Momentum, traditionally examined in sports, is an ability to increase or develop continuously, impacting mental and physical performance in a pattern akin to human preferences, which are complex and non-linear. This research explores momentum in sports, particularly tennis, integrating it with the economic concept of diminishing marginal utility to analyze momentum shifts. Using data from the 2023 Wimbledon men's singles, the study dissects momentum into absolute and relative measures, revealing server advantage and precise models with an R-square value of 0.877. It employs macro and micro perspectives to link momentum with success, affirming its significant impact on win rates and performance dimensions. A GARCH model identifies influential factors in momentum transitions, informing strategies for game control. Applying the model to basketball, specifically a 2024 Clippers-Celtics NBA game, maintains strong predictive capabilities, indicating its broader applicability. Practical recommendations for tennis coaches and players, grounded in empirical findings, conclude the study, emphasizing strategic momentum utilization.

Do not shut up and do dribble: social media and TV consumption

This paper investigates the impact of social media interest and sentiment surrounding the 2020 National Basketball Association’s involvement with the Black Lives Matter movement on the television audience in the United States. Twitter (now known as X) serves as the chosen social media platform, and we determine the sentiment expressed in tweets (messages posted on Twitter) using the XLM-RoBERTa deep language model. Our primary findings indicate that the quantity of users’ posts does not significantly influence TV viewership; instead, the tone of the messages plays a crucial role. Positive messages supporting the NBA’s engagement correlate with an increase in the number of viewers, while those expressing opposition do not. We argue that this asymmetry may stem from a positive elasticity among casual (non-habitual) NBA viewers concerning positive sentiments toward NBA involvement. These viewers are likely to align with the NBA’s stances on civil rights and BLM. In contrast, the core NBA fan base exhibits inelastic demand and is unlikely to cease watching NBA games. A comprehensive set of robustness checks reinforces the validity of our key conclusions.

Estimating winning percentage of the fourth quarter in close NBA games using Bayesian logistic modeling.

This study examined the fourth quarters in the close games in the regular NBA games in the last decade, ranging from the 2013-14 season to the 2022-2023 season. A close game is categorically defined by a scenario where the point differential is confined within a 10-point margin at the onset of the fourth quarter and narrows further to a 5-point disparity by the end of the game. In total, 2,295 close games were identified in this study. Advanced game statistics, including offensive rate, defensive rate, assistance ratio, pace of game, and true shooting percentage, etc., are obtained from the NBA box scores using a python script. Understanding key factors that determine the outcome of the basketball games is critical, as such can be used to develop predictive models for coaches to design game strategies. This study developed a Bayesian Logistic Modeling approach to estimate the winning probability of a basketball team in the fourth quarter, using the pace of the last quarter and a team's shooting percentage. The accuracy of the model is used to evaluate if the model can correctly classify game outcome based on the identified game statistics in the fourth quarter of a game. The binary outcome of the close game is modeled as a Bernoulli distribution. Results reveal that the True Positive Rate and False Positive Rate is 0.93 and 0.07, respectively. Insights from this study can be used to help design coaching strategies in basketball games, illuminating potential tactical pivots that could tilt the game in their favor.

Optimizing Bilingual Sports Commentary under the Guidance of Functional Equivalence Approach

This paper explores the application of functional equivalence theory in enhancing bilingual sports commentary, with a focus on Chinese and English languages. By analyzing commentary from various sports events, including the F1 British Grand Prix, NBA games, FIFA World Cup matches, and League of Legends World Championships, the study identifies key differences and areas for improvement in both language commentaries. Chinese commentary often suffers from clarity issues due to excessive commentators and informal language, while English commentary lacks cultural and idiomatic richness. The research demonstrates that integrating functional equivalence theory can significantly improve the quality of sports commentary by ensuring that it is culturally and linguistically tailored to the audience's experience. This approach not only provides a richer viewer experience but also bridges the gap between different linguistic audiences, maintaining the excitement and context of the sports event.

Integration of machine learning XGBoost and SHAP models for NBA game outcome prediction and quantitative analysis methodology.

This study investigated the application of artificial intelligence in real-time prediction of professional basketball games, identifying the variations within performance indicators that are critical in determining the outcomes of the games. Utilizing games data from the NBA seasons 2021 to 2023 as the sample, the study constructed a real-time predictive model for NBA game outcomes, integrating the machine learning XGBoost and SHAP algorithms. The model simulated the prediction of game outcomes at different time of games and effectively quantified the analysis of key factors that influenced game outcomes. The study's results demonstrated that the XGBoost algorithm was highly effective in predicting NBA game outcomes. Key performance indicators such as field goal percentage, defensive rebounds, and turnovers were consistently related to the outcomes at all times during the game. In the first half of the game, assists were a key indicator affecting the outcome of the game. In the second half of the games, offensive rebounds and three-point shooting percentage were key indicators affecting the outcome of the games. The performance of the real-time prediction model for NBA game outcomes, which integrates machine learning XGBoost and SHAP algorithms, is found to be excellent and highly interpretable. By quantifying the factors that determine victory, it is able to provide significant decision support for coaches in arranging tactical strategies on the court. Moreover, the study provides reliable data references for sports bettors, athletes, club managers, and sponsors.

Investigating the factors that influence NBA draft rankings

The NBA Draft is an annual event for the NBA to select new players, which is significant for both players and NBA teams. In this work, the main objective is to explore whether player draft rankings could reflect a player's career development in the NBA. With this aim, we built three multiple linear regression models based on the 10-year draft rankings collected from 2009-2018 and the NBA career data and college data for these players. The results of these analyses indicate that these variables of NBA players: G, PTS and BLK have the strongest associations with their NBA draft ranks in NBA games and that these variables: TG, FGP, P3PP, PPTS and PSTL in college statistics have strong associations with the future NBA draft rank. However, there are some outliers in the prediction results, which indicates that some abilities valued by the team cannot be reflected by data values.

The association between professional sporting events and police calls for service in San Antonio, Texas

ABSTRACT The influence of sporting events on crime is an important but under-researched area in criminology. Although this literature is growing, it mostly focuses on whether crime changes in the city/area where a sporting event is taking place. Thus, it is unclear whether crime in a different city/state can be affected by airing a sporting event on television. The current study contributes to the literature by investigating the impact of televised professional sporting events by the NFL, NBA, MLB, and NHL on calls for police service in San Antonio, Texas. Specifically, this study examines whether five categories of police calls for service in San Antonio increase or decrease on days in which NFL, NBA, MLB, and NHL games take place compared to days with no games. This study examines this association between March 2020 and March 2021 during which in-person sporting events were not permitted in San Antonio because of COVID-19 restrictions. Results indicate that days with particular sporting events are associated with increases in certain calls for police service, while others are associated with decreases. Our findings suggest that police departments may consider increased patrol on days that certain sporting events take place.

A Data-Driven Machine Learning Algorithm for Predicting the Outcomes of NBA Games

We propose a new, data-driven model for the prediction of the outcomes of NBA and possibly other basketball league games by using machine learning methods. The paper starts with a strict mathematical formulation of the basketball statistical quantities and the performance indicators derived from them. The backbone of our model is the extended team efficiency index, which consists of two asymmetric parts: (i) the team efficiency index, generally based on some individual efficiency index—in our case, the NBA player efficiency index, and (ii) the comparing part, in which the observed team is rewarded for every selected feature in which it outperforms its rival. Based on the average of the past extended indices, the predicted extended indices are calculated symmetrically for both teams competing in the observed future game. The relative value of those indices defines the win function, which predicts the game outcome. The prediction model includes the concept of the optimal time window (OTW) for the training data. The training datasets were extracted from maximally four and the testing datasets from maximally two of the five consecutive observed NBA seasons (2013/2014–2017/2018). The model uses basic, derived, advanced, and league-wise basketball game elements as its features, whose preparation and extraction were briefly discussed. The proposed model was tested for several choices of the training and testing sets’ seasons, without and with OTWs. The average obtained prediction accuracy is around 66%, and the maximal obtained accuracy is around 78%. This is satisfactory and in the range of better results in the works of other authors.

The Gamble of the First Basket: A Study on Betting the First Scorer in NBA Games

The Gamble of the First Basket: A Study on Betting the First Scorer in NBA Games

NBA Game Analysis based on Big Data

As an important sport, basketball has a history of more than 100 years. With the rapid development of basketball, data analysis technology has also been widely used. In basketball games, the data that people see is a set of systematic data formed by professional workers through division of labor and close cooperation, classification and statistical analysis. In addition, based on information on the field, spectators get a general idea of how athletes are performing during the game and predict where the data will go. Based on the above background, this paper discusses the significance and application of NBA game data analysis methods, and shows that in NBA games, data analysis can effectively promote the development of basketball.

Research on the Developing Trend and Strategies of the NBA Games and NBA Players

Since the birth of the professional league, players have become entertainment products for the public. From Paul Arizin, the inventor of the jump shot who also earned part-time money, to LeBron James, who is worth hundreds of millions of dollars, this entertainment maximizes the value of players and promotes the game of basketball to the world. The National Basketball Association is arguably the world’s most competitive professional basketball league. It features all the top players, coaching staff, and trainers. It has been established for 75 years. However, each period of the league has some special trends of it. As the league is stepping into the 2020s era, it’s quite significant that people can observe new trends involving playing styles and players. This paper discusses and investigates the trend of the NBA playing style and player builds using static and situational analysis. This paper also made predictions about the NBA Draft prospects. Then, this paper will present the methods and data, followed by the results and discussions to improve the NBA’s development. Such as the periphery taking IP as the core and spreading it to the periphery; the Industrial chain Logic of IP Event tourism development, and adhering to the “star” strategy to create idols and aggregate the flow of fans.

What are the changes in basketball shooting pattern and accuracy in National Basketball Association in the past decade?

The main research question addressed in this study is if and how the shooting pattern and field-goal accuracy have changed in the NBA league in the past decade. This study analyzes NBA game data from the 2011–2012 regular season to the 2020–2021 season. Field goal attempts are grouped into five categories by the shooting distance. The Mann-Kendall trend test was employed to examine if changes are statistically significant (p < 0.05) over the years. Sixteen equal segments in one basketball game, each with 3 min, were analyzed to examine the shooting pattern in different game segments. Results reveal an increasing trend in the percentage of 3-pointer shooting, which has nearly doubled from 22 to 39%. Meanwhile, the percentage of field goals within the range of 16–24 ft has decreased from 20 to 10%. Field-goal accuracy has shown an increasing trend for all shooting distances except for the 3-pointer shooting. The second and fourth 3-min within each quarter have the highest number of field goals. The first quarter has a higher shooting accuracy than the rest three quarters. In addition, results reveal that the last 3-min in each quarter has the lowest shooting accuracy. Reasons for the patterns of field goals in different segments are discussed from the perspective of game rule changes, the fatigue effects, and coaches’ game strategies. The reasons for changes in activity level and performance in different quarters are also discussed. This study offers new insights into the changes in basketball shooting patterns and accuracy in NBA games in the past decade. Practical meanings of this study for basketball players, coaches, and sports psychologists, as well as the strength and limitations of this study, are discussed.

The Relationship between The Lakers Team and Fans’ Attitude

NBA the National Basketball Association founded in 1946 is one of the most historical leagues and also the most popular one in the recent world. Every day there are millions of people old and young, tall and short, watching the NBA games. The Los Angeles Lakers, founded in 1974, the most famous team in the NBA have run into some trouble, they are losing fans due to their unbeatable performance. The purpose of this study was to find ways to solve the trouble of the Lakers, improve the basketball team, boost the number of fans and get money back. This paper also used qualitative analysis and SWOT analysis listing the aspects that affect the fandom base and how to comfort the unpleasant fans. The research also concluded several methods for the manager of the Lakers to choose from. Thus, the desire of the fans and the advantage and disadvantage of the Lakers team is also discussed in the paper.

Shot fakes as an indicator of successful offense in basketball.

Past research has shown that tactical skills can increase the offensive output in basketball. Laboratory studies have confirmed this and indicated that fakes are useful, but their effectiveness is a function of expertise. In recent times, experts in the field have been able to correctly identify fakes with a higher accuracy. In this study, the primary objective was to investigate the offensive technical-tactical play shot fakes as a possible performance indicator in real basketball games. Furthermore, we evaluated how the attacker's initial offensive positioning and location on court influence the effectiveness of such shot fakes. We examined 45 NBA games using post-hoc video analyses. Though, on an average, a tenth of all points were scored after a shot fake, our data showed a significantly higher offensive effectiveness of possessions with a shot fake compared to the games' average for all offensive possessions. Moreover, shot fakes were found to be more effective being initially open, and were more often used when the focus player was being covered by a defender. In addition, 73% of all shot fakes were successful and advantageous for the attacker. This result, in conjunction with previous laboratory studies in which experts showed an above average probability of detection, points to the importance of time pressure for representative study designs. The evidence from this study proves that shot fakes are an important and effective offensive tool to gain an advantage over the opponent and increase offensive scoring, thereby setting the foundation for future research on shot fakes across sports.

The Effect of the Crowd on Home Bias: Evidence from NBA Games During the COVID-19 Pandemic.

The present study examines a specific type of referee biases, home bias, and analyzes how the presence of fans affects home bias by using NBA games played in empty arenas during the COVID-19 pandemic in the 2020–2021 season and matches played before the pandemic from 2017 to 2020. This research also uses a unique data set from NBA Last Two Minute Reports to assess referees’ performance at the play level. The findings show crowd support does not cause referees to treat home and away teams differently in crucial situations during the NBA regular season, contrary to the results in most prior studies.

OBTracker: Visual Analytics of Off-ball Movements in Basketball.

In a basketball play, players who are not in possession of the ball (i.e., off-ball players) can still effectively contribute to the team's offense, such as making a sudden move to create scoring opportunities. Analyzing the movements of off-ball players can thus facilitate the development of effective strategies for coaches. However, common basketball statistics (e.g., points and assists) primarily focus on what happens around the ball and are mostly result-oriented, making it challenging to objectively assess and fully understand the contributions of off-ball movements. To address these challenges, we collaborate closely with domain experts and summarize the multi-level requirements for off-ball movement analysis in basketball. We first establish an assessment model to quantitatively evaluate the offensive contribution of an off-ball movement considering both the position of players and the team cooperation. Based on the model, we design and develop a visual analytics system called OBTracker to support the multifaceted analysis of off-ball movements. OBTracker enables users to identify the frequency and effectiveness of off-ball movement patterns and learn the performance of different off-ball players. A tailored visualization based on the Voronoi diagram is proposed to help users interpret the contribution of off-ball movements from a temporal perspective. We conduct two case studies based on the tracking data from NBA games and demonstrate the effectiveness and usability of OBTracker through expert feedback.

“Dancing with the Stars,” NBA Games, Politics: An Exploration of Twitter Users’ Response to Events

Microblogging services such as Twitter offer great opportunities for analyzing the reactions of a wide audience with respect to current events. In this paper, we explore the correlation between types of user engagement and events centered around celebrities (e.g., personal or professional events involving Actors, Musicians, Politicians, Athletes).

A comment on Paul, Weinbach, and Wilson’s (2004) “Efficient markets, fair bets, and profitability in NBA totals 1995-96 to 2001-02”

This paper revisits Paul et al. (2004) using a more recent data set to test for inefficiencies in the totals market for NBA games. Using data from the 1995-96 to 2001-02 seasons, Paul et al. (2004) found the market as a whole to be efficient, but that this was not the case for bets on the highest of point totals. Using data from the 2012-13 to 2018-19 seasons reveals a market that is more efficient than that of their earlier work, as the null hypothesis of a fair bet is not rejected for the higher totals. However, winning percentages in excess of 52.4 % were found further in the upper tail of the distribution of points totals relative to the earlier period.