Search Results (29)

In this article, we provide a comprehensive review of machine learning-based sports analytics in baseball. This review is primarily guided by the following three research questions: (1) What baseball analytics problems have been studied using machine learning? (2) What data repositories have been used? (3) What and how machine learning techniques have been employed for these studies? The findings of these research questions lead to several research contributions. First, we provide a taxonomy for baseball analytics problems. According to the proposed taxonomy, machine learning has been employed to (1) predict individual game plays; (2) determine player performance; (3) estimate player valuation; (4) predict future player injuries; and (5) project future game outcomes. Second, we identify a set of data repositories for baseball analytics studies. The most popular data repositories are Baseball Savant and Baseball Reference. Third, we conduct an in-depth analysis of the machine learning models applied in baseball analytics. The most popular machine learning models are random forest and support vector machine. Furthermore, only a small fraction of studies have rigorously followed the best practices in data preprocessing, machine learning model training, testing, and prediction outcome interpretation. Full article

In this study, we analyze the winning percentage of 16 teams that have participated in Major League Baseball since 1901. First, 69 variables for each team are classified into pitching, batting, and fielding using factor analysis, and then the effect of the newly classified variables on the winning percentage is analyzed. In addition, after expressing each team’s winning rate as a fuzzy number using a fuzzy partition, the linear relationship between the previous year and the next year using the fuzzy probability is investigated, and we estimate the fuzzy regression model and Markov regression model using the Double Least Absolute Deviation (DLAD) method. The proposed fuzzy model describes variables that affect the winning percentage of the next year according to the winning rate of the previous year. The estimated fuzzy regression model showed that the on-base percentage allowed by the pitcher and the on-base percentage of the batter had the greatest effect on the winning percentage. Full article

The impact of sporting events on local economies and their spatial distribution is a topic of active policy debate. This study adds to the discussion by examining granular cellphone location data to assess the spillover effects of Major League Baseball (MLB) games in a major US city. Focusing on the 2019 season, we explore granular geospatial patterns in mobility and consumer spending on game days versus non-game days in the Saint Louis region. Through density-based clustering and hotspot analysis, we uncover distinct spatiotemporal signatures and variations in visitor affluence across different teams. This study uses features like game day characteristics, location data (latitude and longitude), business types, and spending data. A significant finding is that specific spatial clusters of economic activity are formed around the stadium, particularly on game days, with multiple clusters identified. These clusters reveal a marked increase in spending at businesses such as restaurants, bars, and liquor stores, with revenue surges of up to 38% in certain areas. We identified a significant change in spending patterns in the local economy during games, with results varying greatly across teams. Notably, the XGBoost model performs best, achieving a test R² of 0.80. The framework presented enhances the literature at the intersection of urban economics, sports analytics, and spatial modeling while providing data-driven actionable insights for businesses and policymakers. Full article

Major League Baseball (MLB) is particularly vulnerable to climate change due to its season duration, geographic footprint, and largely outdoor nature. Therefore, the purposes of this study were to investigate whether U.S.-based MLB fans’ climate change skepticism and experiential processing influenced their climate change risk perceptions and adaptation willingness, and to determine if those relationships were further influenced by fans’ sport identification with MLB. A cross-sectional survey design tested the study’s purposes using a sample (n = 540) of self-identified MLB fans. Data were analyzed using structural equation modeling on the Mplus 8 statistical package to test the hypothesized model. The results indicated consistencies across low and highly identified MLB fans on their climate change risk perceptions and willingness to adapt, but revealed group differences between the factors influencing fans’ risk perceptions of climate change. The findings provide early empirical evidence to support the United Nations’ (UN) Sport for Climate Action Framework, and managerial implications regarding the nexus of climate change and sport consumer behavior research. Full article

The COVID-19 pandemic has led to a dramatic increase in baseball viewership, thereby providing an opportunity to comprehensively explore the determinants of the new audience. To this end, we analyze the preferences of the Taiwanese audience in 2019 and 2020, both before and after the COVID-19 outbreak, through TV ratings based on the effect of outcome uncertainty, tournament factors, consumer availability, and game quality. The empirical findings show that the behavior of the small-scale Chinese Professional Baseball League (CPBL) sports television viewing market differs from that of large-scale markets such as Major League Baseball. Additionally, the effect of the outcome uncertainty of the game is inconsistent before and after the COVID-19 pandemic. New audiences, unlike existing audiences, have been affected by team quality and consumer availability that are statistically significant, but tournament factors are not significant. This study provides the first empirical analysis of the factors driving TV ratings of CPBL games as well as the impact before and after the COVID-19 outbreak as a contribution to filling the gap in sports communication research. The observations can be used by strategic departments of professional teams for their marketing target, to identify potential fans, and to direct their marketing resources towards sustaining or even growing during the pandemic events. Full article

Air quality is a growing environmental concern that has implications for human physical and mental health. While air pollution has been linked to cognitive disease progression and declines in overall health, the impacts of air quality on athletic performance have not been extensively investigated. Much of the previous research focused on endurance sports indicates that air quality negatively impacts athletic performance; however, the effects of air quality on non-endurance elite team performance remains largely unknown. The purpose of this study was to examine the impact of air quality on errors committed by Major League Baseball (MLB) teams, interceptions thrown by quarterbacks in the National Football League (NFL), and overall quarterback performance in the NFL. Linear regression analysis was used to determine the impact of the median air quality index (AQI) of counties with MLB and NFL teams on errors, interceptions, and overall quarterback performance of players on those MLB and NFL teams. AQI was a significant positive predictor of errors and interceptions, indicating increased errors and interceptions with decreased air quality. Similarly, quarterback performance was significantly reduced for quarterbacks from teams in counties with worse air quality. These findings suggest that air quality has a significant impact on performance in the MLB and NFL, indicating impairments in physical and cognitive performance in professional athletes when competing in areas with poorer air quality. Hence, it is likely that air quality impacts athletic performance in numerous sports that have not yet been investigated. Full article

Baseball is a sport that involves a large number of statistics, which are often displayed during broadcast events to show the players’ performance levels. With the advent of big data, the amount and types of data used in broadcasts have increased yearly. However, the use of complex information challenges the audience’s ability to process it. This study considered data types used during broadcasts as the basis for an in-depth exploration of audiences’ experience resulting from the application of visualization. The study also examined the relationship between the contents of broadcast information and audiences’ sports participation, entertainment experience, and cognitive load. Baseball fans with varying levels of experience with handling different types of information were surveyed to understand the variations in their entertainment experiences and cognitive load levels when they watched a baseball game. The results indicated that fans with low participation levels had insufficient viewing experience, such that the use of visualized statistical information did not facilitate their understanding of the game, nor did they gain more pleasure or meaning from the game through the visualized information. Fans with high participation levels already possessed a wealth of baseball knowledge and experience, so providing visualized information did not significantly elevate their viewing experiences either. Moreover, the visualized information caused them to experience varying amounts of additional cognitive load. These results provide a reference that can be used to design sports broadcasts tailored to different information types and fan characteristics, thus improving fans’ viewing experience of sports broadcasts. Full article

There has been a considerable amount of literature on binomial regression models that utilize well-known link functions, such as logistic, probit, and complementary log-log functions. The conventional binomial model is focused only on a single parameter representing one probability of success. However, we often encounter data for which two different success probabilities are of interest simultaneously. For instance, there are several offensive measures in baseball to predict the future performance of batters. Under these circumstances, it would be meaningful to consider more than one success probability. In this article, we employ a bivariate binomial distribution that possesses two success probabilities to conduct a regression analysis with random effects being incorporated under a Bayesian framework. Major League Baseball data are analyzed to demonstrate our methodologies. Extensive simulation studies are conducted to investigate model performances. Full article

This study analyzed the characteristics of pitched baseballs from TV broadcast videos to understand the effects of the Magnus force on a pitched-baseball trajectory using aerodynamic theory. Furthermore, an automatic measurement and analysis system for pitched-baseball trajectories, ball speeds, and spin rates was established, capturing the trajectory of the baseball thrown by the pitcher before the catcher catches it and analyzing its related dynamic parameters. The system consists of two parts: (1) capturing and detecting the pitched baseball in all frames of the video using the YOLOv3-tiny deep learning algorithm and automatically recording the coordinates of each detected baseball position; (2) automatically calculating the average speed and spin rate of the pitched baseball using aerodynamic theory. As the baseball thrown by the pitcher is fast, and live-action TV videos like sports and concerts are typically at least 24 fps or more, this study used YOLOv3-tiny algorithm to speed up the calculation. Finally, the system automatically presented pitching data on the screen, and the pitching information in the baseball game was easily obtained and recorded for further discussion. The system was tested using 30 videos of pitched baseballs and could effectively capture the baseball trajectories, throw points, catch points, and vertical displacements. Compared with the values from the TV broadcast, the average errors on the calculated ball speed and spin rate were 1.88% and 7.51%, respectively. Using the ratio of the spin rate and ball speed as a parameter to analyze the pitching state of the pitcher’s four-seam fastball in the Nippon Professional Baseball and Major League Baseball matches, it was observed that when this ratio increased, the Magnus displacement of the ball increased, thereby decreasing its late break. Therefore, the developed system provides scientific pitching data to improve the performance of baseball pitchers. Full article

To counter a perceived increase in multi-piece fracturing of wood baseball bats, Major League Baseball implemented standards to regulate the quality of wood used in the making of professional-grade baseball bats. These specifications included a minimum density as a function of wood species and a standard related to slope of grain (SoG). Following the implementation of these specifications in 2008, there was a 65% reduction in the multi-piece failure rate. It is hypothesized that a further reduction in the breakage rate can be realized through the implementation of regulations on allowable bat profiles. In the current work, a parametric study was conducted to develop a quantitative understanding of the relationship between bat durability (i.e., resistance to breaking), SoG, and bat profile, thereby obtaining data to support or refute the hypothesis. Finite element models of the bat/ball impact of four different popular bat profiles were created using LS-DYNA software. Similarities and differences between bat profiles impacted at two relatively vulnerable axial locations are presented and discussed. Lastly, the respective bat durabilities for all of the profiles were compared using a probability analysis that considers the SoG, impact location, impact velocity, and it predicts an in-service bat durability. Full article

(1) Background and Objective: Major League Baseball (MLB) is one of the most popular international sport events worldwide. Many people are very interest in the related activities, and they are also curious about the outcome of the next game. There are many factors that affect the outcome of a baseball game, and it is very difficult to predict the outcome of the game precisely. At present, relevant research predicts the accuracy of the next game falls between 55% and 62%. (2) Methods: This research collected MLB game data from 2015 to 2019 and organized a total of 30 datasets for each team to predict the outcome of the next game. The prediction method used includes one-dimensional convolutional neural network (1DCNN) and three machine-learning methods, namely an artificial neural network (ANN), support vector machine (SVM), and logistic regression (LR). (3) Results: The prediction results show that, among the four prediction models, SVM obtains the highest prediction accuracies of 64.25% and 65.75% without feature selection and with feature selection, respectively; and the best AUCs are 0.6495 and 0.6501, respectively. (4) Conclusions: This study used feature selection and optimized parameter combination to increase the prediction performance to around 65%, which surpasses the prediction accuracies when compared to the state-of-the-art works in the literature. Full article

For a large ensemble of complex systems, a Many-System Problem (MSP) studies how heterogeneity constrains and hides structural mechanisms, and how to uncover and reveal hidden major factors from homogeneous parts. All member systems in an MSP share common governing principles of dynamics, but differ in idiosyncratic characteristics. A typical dynamic is found underlying response features with respect to covariate features of quantitative or qualitative data types. Neither all-system-as-one-whole nor individual system-specific functional structures are assumed in such response-vs-covariate (Re–Co) dynamics. We developed a computational protocol for identifying various collections of major factors of various orders underlying Re–Co dynamics. We first demonstrate the immanent effects of heterogeneity among member systems, which constrain compositions of major factors and even hide essential ones. Secondly, we show that fuller collections of major factors are discovered by breaking heterogeneity into many homogeneous parts. This process further realizes Anderson’s “More is Different” phenomenon. We employ the categorical nature of all features and develop a Categorical Exploratory Data Analysis (CEDA)-based major factor selection protocol. Information theoretical measurements—conditional mutual information and entropy—are heavily used in two selection criteria: C1—confirmable and C2—irreplaceable. All conditional entropies are evaluated through contingency tables with algorithmically computed reliability against the finite sample phenomenon. We study one artificially designed MSP and then two real collectives of Major League Baseball (MLB) pitching dynamics with 62 slider pitchers and 199 fastball pitchers, respectively. Finally, our MSP data analyzing techniques are applied to resolve a scientific issue related to the Rosenberg Self-Esteem Scale. Full article

Without assuming any functional or distributional structure, we select collections of major factors embedded within response-versus-covariate (Re-Co) dynamics via selection criteria [C1: confirmable] and [C2: irrepaceable], which are based on information theoretic measurements. The two criteria are constructed based on the computing paradigm called Categorical Exploratory Data Analysis (CEDA) and linked to Wiener–Granger causality. All the information theoretical measurements, including conditional mutual information and entropy, are evaluated through the contingency table platform, which primarily rests on the categorical nature within all involved features of any data types: quantitative or qualitative. Our selection task identifies one chief collection, together with several secondary collections of major factors of various orders underlying the targeted Re-Co dynamics. Each selected collection is checked with algorithmically computed reliability against the finite sample phenomenon, and so is each member’s major factor individually. The developments of our selection protocol are illustrated in detail through two experimental examples: a simple one and a complex one. We then apply this protocol on two data sets pertaining to two somewhat related but distinct pitching dynamics of two pitch types: slider and fastball. In particular, we refer to a specific Major League Baseball (MLB) pitcher and we consider data of multiple seasons. Full article

In 2017, Sports Illustrated (SI) made headlines when their remarkable prediction from 2014 that the Houston Astros (a team in one of the lowest Major League Baseball divisional rankings) would win the World Series, came true. The less-publicised story was that in 2017, SI predicted the Los Angeles Dodgers to win the Major League Baseball (MLB) title. Assessing the forecasting accuracy of experts is critical as it explores the difficulty and limitations of forecasts and can help illuminate how predictions may shape sociocultural notions of sport in society. To thoroughly investigate SI’s forecasting record, predictions were collected from the four major North American sporting leagues (the National Football League, National Basketball Association, Major League Baseball, and National Hockey League) over the last 30 years (1988–2018). Kruskal–Wallis H Tests and Mann–Whitney U Tests were used to evaluate the absolute and relative accuracy of predictions. Results indicated that SI had the greatest predictive accuracy in the National Basketball Association and was significantly more likely to predict divisional winners compared to conference and league champions. Future work in this area may seek to examine multiple media outlets to gain a more comprehensive perspective on forecasting accuracy in sport. Full article

Asians hold a collectivistic culture, and they feel attachment to people who have the same ethnic background. This study explored how roles of ethnic identity influenced fan behaviors of Korean audiences toward Hyun-jin Ryu, the Korean Major League Baseball player. The results showed that ethnic identity influenced player identification, which led to attitudes toward the L.A. Dodgers. Congruence mediated the relationship between ethnic identity and player identification. It is also found that transportation mediated the relationship between player identification and attitudes toward the L.A. Dodgers. These results provide a cultural explanation of fan behaviors of ethnic players. Managerial implications can also be found. Full article