Research Papers Competition

SSAC 2025 Research Papers

2025 Research Paper Finalists

CoachAI+ Badminton Environment: Realistic Badminton Game Simulator for Enhancing Player Performance

Short Abstract:
In recent years, advancements in artificial intelligence (AI) and data collection technologies have revolutionized sports analytics, enabling deeper insights into athletic performance that were previously unattainable. Badminton, a fast-paced and strategy-intensive sport, involves rapid decision-making and complex rally dynamics, making it a challenging yet ideal candidate for exploring the integration of AI in sports analysis. Badminton analysis typically focuses on shuttlecock landing trajectories, player movement patterns, shot type selection, and strategic planning. Accurate analysis is crucial for understanding player decision-making and providing actionable insights, both for in-game tactics and pre-match training. Effective sports analytics can help athletes address weaknesses, exploit strengths, and optimize on-court performance through targeted preparation.

Author(s):
Peng, Wen-Chih

Wen-Chih Peng is a professor in the Department of Computer Science at National Yang Ming Chiao Tung University, Taiwan, where he has held several prestigious leadership positions, including Chair of the Department of Computer Science, Associate Dean of the College of Computer Science, and Vice Director of the Digital Medicine Center. His research expertise spans data mining, machine learning, big data analytics, and sports data analytics, areas in which he has published over 170 scholarly articles in esteemed journals and conferences such as KDD, ICDM, ICDE, AAAI, and IJCAI. A badminton and tennis enthusiast, he has spearheaded the development of CoachAI, an advanced AI-driven data analysis platform designed to assist badminton players in optimizing their strategies through comprehensive match data analysis. His current focus lies in advancing the Badminton Environment, a simulator aimed at modeling matches and identifying key strategies for performance improvement, in collaboration with professional teams such as the Chailease Badminton Team. Deeply committed to the advancement of sports science, Dr. Peng takes pride in integrating his passion for athletics with cutting-edge technologies to deliver impactful contributions to the sports community.

Wang, Kuang-Da

Chien, Yen-Che

Xie, Bo-Zhou

Chen, Yu-An

Tsai, Cheng-Shiuan

Doong,Shao-Jyun

Hung, Jun-Chen

A Machine Learning Approach to Player Value and Decision Making in Professional Ultimate Frisbee

Short Abstract:
In the past decade, Ultimate Frisbee – commonly known as ‘ultimate’ –has transformed from a largely amateur sport to a professional arena with dedicated athletes and multiple leagues including the Ultimate Frisbee Association, the Premier Ultimate League, and the Western Ultimate League. Unlike established professional sports with sophisticated analytical frameworks like baseball's sabermetrics or football's Next Gen Stats, ultimate has historically relied on basic counting statistics such as goals, assists, and blocks, with analysis often limited to post hoc volunteer-tracked metrics. The emergence of professional leagues has been pivotal in driving more thorough data collection, with new tracking systems now capturing unprecedented detail –recording aspects of every throw, including thrower and receiver location, throw outcome, and game time. Despite these advancements, analytics in ultimate are still underdeveloped, leaving room for more refined methods to assess player contributions and team strategy.

Author(s):
Eberhard, Braden

Braden Eberhard is a ML Engineer at Harvard Medical School, specializing in clinical data analysis and predictive modeling. He is passionate about applying machine learning to ultimate frisbee, seeing a unique opportunity to harness analytics in a rapidly growing sport that has yet to fully leverage its potential. As a professional player, Braden has competed in the Ultimate Frisbee Association (UFA) with both the Salt Lake Shred and Boston Glory, helping the Shred secure the West Division title and a national runner-up finish in 2023. Outside of playing, Braden gives back to the community by coaching youth teams, leading the Utah Swarm U20 team to National Championship titles in 2022 and 2023. In his free time, Braden enjoys playing chess, reading, and volunteering within the Boston community.

Miller, Jacob

Jacob is a data scientist at Qualtrics and a professional ultimate frisbee player in the Ultimate Frisbee Association (UFA), currently signed with the Salt Lake Shred. He received All-UFA Third Team honors in 2023 and led the league in hockey assists each of the last two seasons (the most important counting stat). In 2022 and 2023 he coached the Utah Swarm U20 boys team to back-to-back national championship titles. He earned his BS and MS in Statistics from BYU. When he's not training or working, his free time is often spent on the next sports analytics project while watching basketball or football.

Sandholtz, Nate

Nate Sandholtz is an Assistant Professor in the Department of Statistics at Brigham Young University.  He holds a PhD in Statistics from Simon Fraser University.  Much of Nate's research focuses on using statistics to inform strategic decisions in sports, with applications in basketball, soccer, football, tennis, and wheelchair rugby.  Prior to joining BYU, Nate was a postdoctoral fellow in the Department of Mechanical and Industrial Engineering at the University of Toronto.  He also worked as a Basketball Operations Analyst for the Sacramento Kings during his PhD.

Evaluating Player Actions in Professional Counter Strike using Temporal Heterogeneous Graph Neural Networks

Short Abstract:
In recent years, electronic sports (esports) have gained popularity, extending the existing landscape of the sports industry. Counter Strike 2 (CS2), a first-person shooter team game, stands as one of the most prominent esports titles in 2024.In this esport, two teams face off within a match, taking turns as attackers (Terrorists - Ts) and defenders (Counter Terrorists - CTs). A match consists of2-minute rounds where Ts must plant a bomb at one of two bomb sites, while CTs must prevent it or defuse the bomb. The first team to win 13 rounds wins the match. With tournaments organized in front of large audiences and professional teams competing for substantial prize pools, the stakes of the professional scene are high. Despite these facts and the abundance of available data, only a few artificial intelligence-driven solutions have been explored so far regarding individual and team performance enhancement, and it has not yet gained much popularity in practical use.

Author(s):
‍Szmida, Patrik Peter

Patrik Peter Szmida, aged 24, was born and raised in Hungary. He holds a Master’s diploma with honors (2025) in Computer Science Engineering from Budapest University of Technology and Economics. In his studies he specialized in artificial intelligence (AI), with a focus on the mathematical foundations of AI models and neural networks. He participated in the university's Students’ Scientific  Conference, where his work earned first place in the Neural Networks category. He has been working as a software developer for the past two years.Patrik has a strong background in both traditional sports and esports. He played basketball for ten years before transitioning to Counter-Strike esports, achieving success in regional tournaments in both disciplines. His experience in competitive sports naturally led to his interest in sports analytics.Throughout his university studies, he worked on sports analytics projects across multiple disciplines, including basketball, soccer, and Counter-Strike esports, leveraging AI-driven innovations to drive advancements in the field.

Toka, Laszlo

László Toka is currently an Associate Professor at Budapest University of Technology and Economics, vice-head of HSN Lab, and a member of the HUNREN-BME Cloud Applications Research Group. He received his PhD from Telecom Paris Tech in2011, he was with Ericsson Research from 2011 to 2014, then he joined the academia with research focus on sports analytics, artificial intelligence, networks and cloud computing.

Causal Impact of Offensive Linemen on Pass Plays

Short Abstract:
‍Offensive linemen play a pivotal role in determining the outcome of pass plays in football, yet their contributions are often undervalued or misunderstood. Traditional analytics tools rely heavily on correlation-based metrics, which can provide insights but fail to capture the intricate cause-and-effect relationships that define the linemen's impact. For example, while correlation may highlight an association between quarterback pressures and incomplete passes, it does not address the causal pathways linking specific offensive linemen actions to these outcomes. This gap in understanding limits the precision and utility of such metrics for decision-making in player evaluation, development, and in-game strategies.

Author(s):
‍Jenkins, Ben

Ben Jenkins is a senior data scientist at SumerSports and a PhD student at Florida Atlantic University. He is passionate about statistics, and particularly applying it to professional sports. When he isn’t writing in the third person, he enjoys spending time with his family and fiancé. His favorite sports team is the Denver Nuggets and will argue that Nikola Jokic is a top ten player of all time.

Do Behavioral Considerations Cloud Penalty-Kick Location Optimization in Professional Soccer: Game Theory & Empirical Testing using Polynomial Regression and ML Gradient Boosting

Short Abstract:
In soccer, penalty kicks (PKs) are taken with fair regularity (~ once in four matches) and often constitute high-leverage, or game-pivotal, events given the sport’s low-scoring nature. In a tabulation of 294,970 international, professional league, and professional cup match results recorded on footystats.org, we find that 1-0 and 1-1 are the most common professional full-time match scorelines, occurring 17.9 and 11 percent of the time, respectively. These outcomes are followed by 2-1 (8.5%) and 0-0 (7.7%). Across all recorded match outcomes, average full-time goals per professional match are 2.85. In the 2022-23 EPL, matches averaged 0.26 PKs and 0.194 PK conversions, equivalent to about 6.8% of goals scored according to tabulations of data from transfermarket.com. In 2023-24, this percentage rose to 7.6%. Herein, we examine whether professional penalty-takers strictly optimize on expected conversion-rate when choosing shot location, or whether behavioral considerations, such as “looking credible” by not missing the goal space entirely, are also at play.

Author(s):
Uribe, Alivia

Ava Uribe is a current senior Sport Management and Sport Analytics student at Syracuse University. Uribe recently completed her second season with the Syracuse University Women’s Soccer team, and in her youth career has represented the U.S. Youth National Team from Under-14 to Under-18. With the U.S National Team, she competed internationally in tournaments such as the UEFA competition in England as well as international friendlies across Europe. She aspires to play professionally post-graduation and has focused her academic and athletic experiences on performance analysis in a variety of sports, especially soccer. As a primary penalty kick taker for the Syracuse Orange, Uribe developed a research interest in penalty kick trends at the professional level, particularly as major international tournaments increasingly see matches decided by shootouts. Her analysis has provided valuable insights into goal conversion strategies, which she has shared with her coaches and teammates to enhance performance in the highly competitive ACC. Syracuse University player page: cuse.com/sports/womens-soccer/roster/Ava-Uribe/24409

Sanders, Shane

University. He conducts research in the areas of player performance analytics with emphasis on team and player (sub-)optimization. He also studies issues of player valuation and league design. Sanders has consulted on basketball roster construction for teams in the EuroLeague and NCAA and has advised NBA teams on cross-league player projections. Sanders 88 academic journal articles, many in top journals of economics, statistics, finance, and sport (J of Business & Economic Statistics, J of Behavioral & Experimental Finance, Economics Letters, J of Sport Management, J of Sports Economics, Social Indicators Research, and J of Quantitative Analysis in Sport among them).  His research has been supported by research grants from FIFA, PARCC, and the Mercatus Center Policy Analytics Program. Sanders’ research has been cited in a U.S. Supreme Court sport antitrust case (American Needle, Inc. v NFL), as well as in leading media outlets such as USA Today, NPR Here and Now, MSNBC, Globe and Mail, Fox Sports, TrueHoop, and The Late Show with Stephen Colbert. Last year, Sanders was a Research Finalist at MIT SSAC for his joint work (with Justin Ehrlich) on NBA advanced shot charts and the increasing 3PA dispremium in the League.  He also also presented his work at Carnegie Mellon Sport Analytics Conference, the Harvard New England Symposium on Statistics in Sport, and the SABR Analytics Conference. Institution page: falk.syr.edu/people/sandersshane/

Ehrlich, Justin

Dr. Justin Ehrlich is an Associate Professor specializing in sport analytics, machine learning, and computer science. His diverse research portfolio spans virtual reality, 3D human pose estimation, advanced visualization, sports rating and ranking, the business of sport, risk analysis for CTE in football players, and biomechanical assessment. As a faculty member in Syracuse University's Big Data Cluster, Dr. Ehrlich focuses on big data applications, performance analytics, and advanced visualization tools such as shot charts.His innovative work has been showcased at the MIT Sloan Sports Analytics Conference and published in journals including the Journal of Behavioral & Experimental Finance, JAMA, Public Choice, and PLOS ONE. Dr. Ehrlich has also conducted extensive golf research in collaboration with the University of Nevada, Las Vegas, exploring topics like the effects of weather on performance, optimizations in swing sequencing, and the impact of swing consistency on course outcomes.Institution page: falk.syr.edu/people/ehrlich-justin/

Reade, James J.

Dr. James Reade is a Professor of Economics at the University of Reading in the UK, having previously worked at the Universities of Birmingham and Oxford, and completing his PhD at Oxford. His research interests are in the economics of sport, with particular applications to football (soccer). His favourite football team is Oldham Athletic (in Greater Manchester, UK).Professional webpage: sites.google.com/site/jjamesreade/

Singleton, Carl

Dr. Carl Singleton is currently Senior Lecturer of Economics at the University of Stirling, as well as a reasearch fellow at the Institute for Labor Economics in Bonn, Germany. His primary research focus is on Macroeconomics and Labour Economics, with particular interests in business cycles, wage determination, and inequality issues. Carl has also published several papers that test economic theory using sports data. These include studies of superstar salaries, the functioning of betting and prediction markets, and the impact of the social context on decision making and judgement bias. Carl is a major sports fan. His football team is Derby County FC, from his hometown in England. In US sports, he follows the NFL closely and is a Buffalo Bills fan.Institution page: www.stir.ac.uk/people/1968994

Transformer-Based Baseball Modeling for Pitch Outcome Prediction and Strategy Optimization

Short Abstract:
The intricate duel between pitcher and batter lies at the heart of baseball, where each pitch can significantly alter the trajectory of a game. Predicting the outcome of individual pitches is a fundamental challenge with profound implications for optimizing defensive alignments, pitch sequencing, and overall game strategy. Traditional analytical methods have predominantly relied on aggregate statistics or heuristic strategies, such as evaluating player-specific batting averages by pitch type or adhering to conventional pitching philosophies like "hard in, soft away". While these approaches offer some insights, they often lack the granularity and adaptability needed to capture the rich context and temporal dependencies inherent in sequences of pitches.

Author(s):
Kneita, Declan

Declan Kneita is a senior undergraduate student majoring in Computer Science at Northwestern University, with a strong background in software engineering and machine learning research. He aspires to work as a data scientist or software engineer in sports analytics after graduation. A lifelong baseball fan, his passion for the game grew from playing and watching the Cubs and White Sox while growing up. In his free time, he enjoys watching and playing sports and playing guitar.

Beyond the Box Score: Using Psychological Metrics to Forecast NBA Success

Short Abstract:
Risk assessment of potential recruits is of prime importance to all NBA franchises. Although most scouting focuses on physical performance statistics, there is general agreement that psychological factors also play an important role in determining success. Accurate psychological assessment of potential recruits can be difficult due to limited access to athletes, the time required to complete the assessments, and the self-reporting nature of traditional psychology questionnaires. In this paper we explore applications of language psychology metrics using machine learning and survival analysis techniques to predict success in the NBA. We found that we could predict which athletes would make it onto an NBA roster with an accuracy of 63% without any physical attributes included in the model. In contrast, a model built just using NCAA playing statistics achieved an accuracy of 78%, and combining physical statistics with the psychological features boosted the performance to 83%. Adding in physical attributes such as age, height and weight, along with the NCAA conference the athlete played in increased the accuracy further to 87%.

Author(s):
Farrell, Sean

Sean Farrell is a data scientist with over a decade of experience spanning machine learning, graph theory, natural language processing, generative AI, and computer vision. He has applied his expertise across a wide range of industries including law enforcement and national security, health, education, emergency services, and professional sports. He has worked with diverse organizations from government agencies and academia to large corporations, startups, and professional sporting bodies. Before transitioning to data science, Sean earned his Ph.D. in high-energy astrophysics and spent nearly a decade in academia hunting for rare types of black holes. He is an avid sports fan (particularly Australian Rules Football) and spends a lot of his spare time applying his predictive modelling skills to various codes.

Laity, Ethan

Laughlin, Dave

Oliver, Dean

Pennebaker, James W.

2025 Poster Presenters

A New Framework to Estimate Return on Investment for Player Salaries in the National Basketball Association

Short Abstract:
Methods to assess the ongoing financial performance of invested monies are essential for financial analysts. Examples are ubiquitous: mutual fund fact sheets report historical returns, publicly-traded companies report quarterly earnings to shareholders, and lenders report on defaulted and delinquent loans. In the vast majority of these cases, both the cash inflows and outflows of invested capital may be recorded as market prices. This makes the financial return calculations rudimentary.

Author(s):
‍Lautier, Jackson

Jackson P. Lautier is an Assistant Professor in the Department of Mathematical Sciences at Bentley University. Prior to Bentley, Jackson spent nearly 10 years working at Prudential Financial, Inc. as an actuary in various roles, including risk management, investment strategy, and quantitative finance. Jackson is a Fellow of the Society of Actuaries, a Chartered Enterprise Risk Analyst, and a Member of the American Academy of Actuaries. He holds a PhD in Statistics and a BA in Mathematics/Actuarial Science, each from the University of Connecticut. Jackson lives in Connecticut with his wife Sandra and two daughters, Penelope and Piper. In his spare time, he enjoys spending time with his family, playing tennis, playing basketball, practicing yoga, cycling, traveling, reading novels, attending live events, and rooting for the New York Knicks.

Enhancing NBA True Shot Charts: A Probabilistic Spatial Approach to Rebounding and Possession Value

Short Abstract:
It’s the last five seconds of regulation, and your team trails by one point, but the ball is in your hands. Tick, tick. The defense is physical and smothering. Tick. You pull up for the game winning shot. Tick. Ball hits back rim and bounces out... BEEP! What happens next? Hopefully your big got the putback, otherwise, time to pray to the refs for a foul. Everything comes down to Plan B. Traditional shot charts, which focus solely on made baskets, fail to capture these crucial dynamics.

Author(s):
Stephanos, Koi

Koi Stephanos is a Basketball Software Engineer for the Charlotte Hornets, currently in his first season with the organization. He holds a Master’s degree in Applied Computing and earned second place in the 2022 Sloan Research Paper Competition. This year’s paper builds on his winning capstone project from the 2024 NBA Future Analytics Stars program. Off the court, Koi and his wife, Emma, are proud parents who recently welcomed their second daughter.

exPress: Contextual Valuation of Individual Players Within Pressing Situations in Soccer

Short Abstract:
Pressing is a critical tactical component in modern soccer, enabling teams to disrupt their opponents’ build-up play and create advantageous scoring opportunities. Its prominence has grown in recent years, exemplified by high-performing teams like Liverpool and Manchester City, whose aggressive pressing systems have been instrumental in their success. By applying coordinated pressure on the ball carrier and surrounding players, pressing not only forces errors but also facilitates quick transitions to offensive plays.

Author(s):
‍Lee, Minho

Minho Lee is a Ph.D. student at Saarland University, focusing on the development of machine learning models for injury identification in football matches. His research interests extend beyond injury analysis to encompass tactical analysis, performance analysis, and a variety of other topics within sports analytics. In addition to his doctoral research, Minho organizes the Korea AI Research Society for Sports (KAISports), fostering collaboration and innovation in the intersection of AI and sports science. Minho is also a passionate football fan who loves both playing and watching the game, and he is a dedicated supporter of FC Seoul and Manchester City.

Geonhee, Joe

Geonhee Jo is a master's student at the University of Seoul, focusing on using AI-based methods to analyze player performance in football matches. His research also spans tactical analysis and data verification, demonstrating his broader interest in football analytics. In particular, he is fascinated by how coaches’ tactical preferences and players’ decision-making can be systematically captured and analyzed through data. A dedicated soccer enthusiast, he hopes that the research will ultimately contribute to better strategies and decisions in football matches.

Miru, Hong

Miru Hong is a student at the Department of Computer Science at Inha University. He is passionate about exploring various ways to analyze and understand football. His main focus is on analyzing meaningful relationships within numbers and using that analysis to assist in making better decisions. He also believes that embedding player information can help identify a player's growth trajectory and find players suited for specific tactics. He is also a passionate supporter of Everton.

Pascal, Bauer

Since 2019, Pascal has been providing evidence to support decision-making by sports experts. With a background in mathematics and computer science, he joined the German Football Association (DFB) as a Data Scientist, where he now leads the Sport-IT & Data Analytics Department. Additionally, to his work at the DFB, Pascal leads a Sports Analytics Chair at Saarland University. He holds a PhD from Tübingen University and gained experience as a part-time data scientist at Zelus Analytics. He also holds a UEFA A-level coaching license and has 10 years of experience in semi-professional football (soccer).

Sang-Ki, Ko

Sang-Ki Ko received a B.S. and Ph.D. degree in computer science from Yonsei University, Seoul, South Korea, in 2010 and 2016, respectively. He is currently working as an Assistant Professor at the Department of Artificial Intelligence of University of Seoulin South Korea since 2023. His research interest includes both the theoretical and practical side of computer science. Since 2020, he has been serving as an advisory professor for Fitogether Inc., a specialized sports science company. Additionally, in 2024, he established the Korea AI Research Society for Sports (KAISports) and has been actively fostering a community focused on advancing sports science innovation through AI technology in South Korea.

Manager Over and Underachievement (MOU) Index: Ranking Soccer Managers

Short Abstract:
Data analytics in soccer has seen significant development in recent years. Most elite football clubs employ data analytics departments and many use data to motivate their decisions. The product that is delivered to fans has also changed, with pundits and commentators now regularly citing advanced statistics in broadcasts. In this time many statistics have been developed to judge player performance, but comparatively few to analyze team managers

Author(s):
‍Ferridge, George

George is currently a final year Ph.D. student in Economics at the University of Warwick. He previously attended Georgetown University where he completed a course including a double major in Economics and Psychology, with a minor in Mathematics. He then completed his Master of Research (with distinction) from Warwick. His research is focused on behavioural economics and data science, with a special interest for public policy projects, gender economics, and sports economics. His work includes collaborations with the UK Gambling Commission and Warwickshire Police, extensions of Kahneman and Tversky’s “Peak-End” memory finding, and work on the barriers to sexual violence reporting. Having been born in London but raised in Boston, George is an avid fan of Chelsea FC, the New England Patriots, Boston sports teams, and Formula 1.

Doinkalytics: A New Paradigm in National Football League (NFL) Placekicking Evaluation

Short Abstract:
Kickers account for over 30% of scoring in the NFL. All 20 of the NFL’s all-time leading scorers have been kickers. Made and missed field goals commonly determine the outcomes of drives, games, and even entire seasons. Unfortunately, analyses of these vital performances remain inadequate, and conventional place-kicking metrics fail to accurately characterize some of the most noteworthy performances in professional football.

Author(s):
‍Dube, Lorenzo

Queralt, Samuel

Fink, Joshua

Goldsberry, Kirk

Bushong, Vanna

An Extensive Investigation of Strategies in Baseball

Short Abstract:
At numerous points throughout the course of a baseball game, a team's manager must choose an action from a set of multiple possible actions. For example, before every at-bat they must decide whether to stick with the current batter or replace them with a pinch hitter. They must also decide when to relieve their current pitcher and which reliever to use. These decisions can have a significant effect on the outcome of a game and are often heavily scrutinized and criticized when they seemingly backfire, like Kevin Cash's decision to relieve a hot-handed Blake Snell in Game Six of the 2020 World Series or Aaron Boone's decision to use Nestor Cortes against Freddie Freeman in Game One of the 2024 World Series.

Author(s):
Melville, William

William Melville received his undergraduate degree in applied and computational mathematics at BYU in 2020 before starting a job as an analyst with the Texas Rangers. He returned to BYU in 2022 where he is currently pursuing a PhD in computer science. His research focuses on applications of game theory to baseball strategy.

Mott, Tristan

Tristan Mott grew up in Austin, TX and is an undergraduate senior in computer engineering and computer science at BYU. He is passionate about researching baseball analytics and playing fantasy baseball and football. Prior work includes collaborations with the Texas Rangers and the BYU baseball team. In his free time, he enjoys fly fishing, backpacking, and playing guitar.

Grimsman, David

David Grimsman is an Assistant Professor in the Computer Science Department at Brigham Young University. He completed BS in Electrical and Computer Engineering at Brigham Young University in 2006 as a Heritage Scholar, and with a focus on signals and systems. After working for BrainStorm, Inc. for several years as a trainer and IT manager, he returned to Brigham Young University and earned an MS in Computer Science in 2016. He then received his PhD in Electrical and Computer Engineering from UC Santa Barbara in 2021. His research interests include multi-agent systems, game theory, distributed optimization, network science, linear systems theory, and security of cyberphysical systems.

Archibald, Christopher

Christopher Archibald is an Assistant Professor of Computer Science at BYU, where he has been since 2019.  His research focuses on Artificial Intelligence and Strategic Reasoning, including Sports Analytics. He received his undergraduate degree in Computer Engineering from BYU in 2006 and a PhD in Computer Science from Stanford University in 2011 under the supervision of Yoav Shoham.  From 2011 to 2013 he was a Postdoctoral Fellow at the University of Alberta under the supervision of Michael Bowling.  From 2013 to 2019 he was an assistant professor at Mississippi State University. He enjoys teaching, playing games with his kids, and learning about obscure sports.

Revolutionizing Formula 1 Broadcasting: Unveiling the Impact of Personalized Virtual Advertising on Brand Recall through eyetracking

Short Abstract:
Virtual Advertising, first introduced in the mid-1990s in the USA (Sander & Altobelli, 2011; Porter, 2022; Leadsom, 2023a; Goldman,2023), has been significantly advanced by companies such as Supponor, Vizrt, HEGO, Broadcast Virtual, UniqFEED and AE Live, which are at the forefront of its development. This technology allows for the real-time replacement of physical perimeter boards with virtual ones, presenting targeted ads to local broadcast audiences (Supponor, 2020; Turner & Cusumano, 2000; Burgi, 1997). In-person spectators do not see these virtual advertisements, as they are overlaid only on the broadcasted version of the event (Cianfrone et al., 2006). The 2006 FIFA World Cup in Germany marked a pivotal moment in the evolution of virtual advertising, enabling advertisers to deliver region-specific advertisements tailored to diverse global audiences. As a result, viewers in different parts of the world, such as America and Germany, were presented with different advertisements displayed on the stadium boards (Goldman,2023). Similarly, the 2024 UEFA European Championship highlighted virtual advertising's success, with Coca-Cola tailoring region-specific ads to appeal seamlessly to local preferences in Europe and Asia (PTF Blog, 2024). From then until today, numerous prestigious sports organizations, leagues, and teams across various disciplines, including Football (e.g., UEFA, La Liga, Serie A), Hockey (NHL, IIHF), Rugby (World Rugby, NRL), Cricket (Cricket Australia, New Zealand Cricket), and others, have adopted virtual advertising. Virtual advertising has since expanded its possibilities, offering dynamic, region-specific content delivery, innovative solutions like virtual billboards, seat covers, and on-field graphics, and enabling advertisers to optimize revenue while enhancing viewer engagement and broadcast quality (Broadcast Virtual, Website).

Author(s):
Alexopoulos, Konstantinos

Currently, Konstantinos is pursuing a Ph.D. at the University of Athens, focusing on how emerging technologies like VR and AR are transforming sports viewing experiences and unlocking new sponsorship opportunities. His academic journey also includes a Master’s in Sports Marketing, where his research centered on the potential impact of Personalized Virtual Advertisements on brand recall and recognition, utilizing eye-tracking tools to analyze consumer engagement. This research has garnered global recognition, with presentations at prestigious international conferences such as the 12th International Conference on Contemporary Marketing Issues and the 19th MIT Sloan Sports Analytics Conference. Professionally, Konstantinos has applied his academic expertise to roles such as the Customer Success department at Palowise, where he managed high-profile clients across industries including insurance, banking, and media, leveraging data-driven strategies and crisis management to deliver results. As a Media Distribution Analyst at ICARUS Sports, he collaborated with global broadcasters like beIN SPORTS and EDGEsport, delivering over 300 media reports for notable clients such as Extreme E, the Invictus Games 2023, and Brave CF. A pivotal moment in his career came during his four-year participation in F1 in Schools as a Team Leader, where he created the official Facebook community to connect participants from around the globe. During his undergraduate years, he served as Head of Marketing and Business Plan at Prom Racing Team, the Formula Student team representing the National Technical University of Athens. In this role, he secured over €100,000 in sponsorships and organized a historic rollout event at the Olympic Athletic Center of Athens, which welcomed over 1,000 attendees. Whether advancing research or developing strategies for leading brands, Konstantinos thrives at the intersection of data, technology, and sports storytelling.

Mochla, Vagia

Tsourvakas, George

The Adaptability Index: An Information Theoretic Framework for Measuring Player Adaptability

Short Abstract:
Since the “super team” era in the NBA started, understanding a basketball player’s offensive adaptability has been crucial to team construction. This holds true of all positions, skill levels, and usage rates. The best, highest usage players are expected to team up with other high usage players and must adapt to each other’s playstyles in a way that maximizes the output from all players. Power forwards and centers are not only expected to grab rebounds and score from in the paint, but also space the floor and score further away from the basket more than ever. The “3” or small forwards are increasingly taking advantage of all the space, running offenses and creating opportunities for others as well as creating their own shots from all areas of the court. Even point guards are getting bigger and stronger, not just shooting from the perimeter but also scoring in the paint when available. Without at least a couple players on the team that are adaptable, it seems that offenses can become stagnant and predictable and star players’ potentials can be wasted.

Author(s):
Mbeledogu, Dubem

Dubem Mbeledogu is a data scientist at Meta, where he focuses on Meta AI and Facebook Search product analytics. Prior to joining Meta, Dubem was a data scientist and management consultant at Bain & Company, working on a variety of projects that combined business strategy with data science. Before transitioning into data science, Dubem worked as a process design engineer at ExxonMobil designing refineries and chemical plants. An enthusiast for applied mathematics, Dubem has a particular passion for operations research and optimization. He enjoys integrating his love for math with his other interests, including sports and business. Dubem holds a bachelor’s degree in chemical engineering from Purdue University and an MBA with a focus in Business Analytics from the MIT Sloan School of Management.