Details

The Sloan Sports Analytics Conference showcases cutting-edge research that is frequently featured in top media outlets throughout the world and has even changed the way sports are analyzed. The Research Papers Competition is an ideal way to build your reputation within the field of sports analytics.

This year’s competition will feature six sports tracks – Basketball, Baseball, Soccer, Football, Business of Sports, and Other Sports.

Submissions are now open for abstracts. Please submit your research paper abstract by 11:59pm ET on Sunday, October 01, 2023.

Abstracts will be selected based on the novelty, academic rigor, and impact of the research.

All submissions will be required to be open-source and a link to the author's GitHub repository or other repository supporting the research will be required.

Please refer to our Research Papers Rules page for full details on the submission and evaluation process. We look forward to reading your contribution!

Rules

Competition Format

The competition consists of the following phases:

  1. Abstract Phase

Authors submit abstracts. Based on the judged merits of their abstract submissions, a select group of authors will be invited to submit full manuscripts.

  1. Full Manuscript Phase

Invited authors submit full manuscripts. Referees will evaluate every manuscript, and authors of the best submissions will be invited to give a presentation on their findings at the conference. The referees will also select a separate set of authors who will be invited to present their work during a poster session, as well as a final set of three authors to give a deep-dive of their work in an open-source workshop.

  1. Conference Phase I

     a. Presentations

Invited authors will present their findings during the first day of the conference. Based on the quality of the presentation and manuscript, one paper per sports track (see tracks below) and one wildcard will be selected to present at the conference in front of a panel of industry experts. The judge scores will be tabulated and the winners will be announced following presentations.

     b. Poster Competition

All posters selected for the conference will be entered into a competition for Best Poster, determined by a combination of a fan and judges vote during the weekend of the conference.

Note: this competition is independent of the presentation finals, and none of the posters will advance to the presentation finals.

Timeline (all times Eastern Time)

Abstract submission due – Oct. 01, 2023, 11:59 p.m. EST

Full paper requests sent out – Mid-October 2023

Full paper submission due (if selected) – Dec. 01, 2023, 11:59 p.m. EST

Finalists and posters announced – Mid-January 2024

Submission of poster (if selected) – Early-February 2024

Submission of presentation (if selected) – Mid-February 2024

Conference presentations (if selected) – Conference Day

Open-Source Requirement

For the Sloan Sports Analytics Conference, the Research Papers competition has been a tremendous opportunity for researchers to both share their work with the community and improve the application of analytics across sports. We are excited to continue requiring all papers to be open-source for SSAC 2024 to further the impact of the great work of researchers in the industry.

Open-source research helps advance our mission to democratize analytics in sports by allowing researchers to build on top of the models and methods of their peers, both amplifying the effect of their research and better enabling widespread adoption of their work. We strongly believe that continued research into sports analytics is what makes our games more exciting and participants more effective. 

All papers will be required to submit a link to the team's GitHub repository, or another open-source repository, with the data used to conduct the research. This should include any publicly available data or private data used in the research. For any private / proprietary data, please use your best judgement to anonymize any personal information before sharing publicly. The code running the models is not required to be submitted, but is encouraged, as it contributes to the communal spirit of open-source work by which researchers build off of each other's work to further the application of analytics across sports.

Sports Tracks

Based on abstract content, all submissions will be entered into one of the following Sports Tracks:

  1. Basketball – All submissions related to the sport of basketball.
  2. Baseball – All submissions related to the sport of baseball.
  3. Soccer – All submissions related to the sport of soccer.
  4. Football – All submissions related to the sport of American football.
  5. Business of Sports – All submissions related to the business of owning, managing, or marketing a sport, or to new technology or ideas which could change the face of the sport.
  6. Other Sports – All submissions related to the playing of a sport that is not included in the above Sports Tracks.

Abstract Guidelines

Abstract submissions should be submitted online, and must use the following guidelines:

  • Abstracts must contain fewer than 500 words, including title and body.
  • Abstracts may include up to two tables or figures combined (e.g.  1 figure and 1 table, or 2 tables).
  • Each abstract should contain the following sections:
  • Introduction – What question is this research trying to answer? Why is it an important question for the industry?
  • Methods – Description of relevant statistical methods used, including data sources or data collection procedures
  • Results – Description of actual (not promised) results along with relevant statistics
  • Conclusion – The overall takeaway from the study, including how the results will impact the sports industry

Evaluation of Submissions

The conference seeks submissions that report research pertaining to the use of analytics in the sports industry. We are open to contributions ranging from evaluating players and game strategies, to examining the success factors for sports business. In the abstract and full paper submission process, research will be evaluated on, but not necessarily limited to, the following criteria:

  • Novelty of research – Does the research provide interesting insight into new models or challenge existing beliefs?
  • Academic rigor / validity of model – Are the methodologies of the model and results fundamentally sound and appropriate?
  • Reproducibility – Can the model and results be replicated independently?
  • Application – What are the applications or potential applications of the insights from the research?

In evaluating presentation finalists at the 2024 SSAC, the above factors will be supplemented by the following criteria, as judged by a panel of academics and industry executives from team management and sports business operations:

  • Interest / impact – Is there significant interest in the proposed question in the field of study or the community at large? What are the benefits or impact of the model or application?

The Research Papers team will review all abstracts. The Review Committee will evaluate all manuscript submissions. The Review Committee consists of the Research Papers team, as well as academic professors and experts from top universities in fields including statistics, information sciences, and economics. The industry panel that makes the final winner selection will decide on the basis of the paper and the presentation at the 2024 Sloan Sports Analytics Conference. In these final evaluations, more weight will be given to the final presentation, specifically the highlighted application and impact of the research.

Conflict of Interest Policy

Our objective is to ensure an unbiased evaluation of submissions throughout the process. We are aware that members of the evaluation committee may have had relationships with authors who have submitted papers. When possible, potential conflicts of interest are avoided by minimizing the review of research by the following:

  • Authors who have collaborated with the reviewer on previous submissions
  • Current or former students who worked with the reviewer
  • Colleagues from the same organization
  • Any other previous relationships with the author that may prevent an unbiased evaluation of the paper

All potential conflicts of interest will be managed as best as possible while still maintaining the quality of the review process. Final reviews will occur without knowledge of the names of the authors.

Rights and Permissions

All authors retain ownership rights to the research and the right to publish the research after the conference. Upon submission, authors grant access to 42 Analytics to make their research available for public viewing online and in print, for conference use for the Sloan Sports Analytics Conference. Authors are responsible for obtaining permission from third parties to reprint copyrighted information such as data, tables, or figures that may be protected by copyright.

SSAC 2023 Research Papers & Authors Profiles

We received multiple research papers submissions for various industries, functions, and sports. Please review our SSAC 2023 research papers below.

2023 Research Papers Finalists

A Game Theoretical Approach to Optimal Pitch Sequencing
Short Abstract:
This paper presents a game theoretical solution to the difficult challenge of optimal pitch sequencing. We model the batter/pitcher matchup as a zero-sum game and determine the equilibrium strategy for both the pitcher and batter. We conclude that the Stackelberg equilibrium and our newly defined decision point equilibrium serve as effective pitch sequencing strategies.
Author(s):
William Melville
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 baseball analytics. His passion for baseball runs much deeper than just the analytics; he also has a great appreciation for the equipment of the game and makes wooden bats in his home woodshop.
Jesse Melville
Jesse Melville is a recent Graduate of Brigham Young University with a degree in Computer Science with an emphasis in data science. Jesse enjoys finding machine learning applications in sports and science. He enjoys playing and watching sports and is BYU's #1 Football Fan. He plays Keeper on collegiate intramural teams and is the best in his peer group. He is an avid reader of Brandon Sanderson's work.
Theo Dawson
Theo Dawson is from Jackson Hole, Wyoming. He is currently in his final semester at Brigham Young University studying Computer Science with an emphasis in Data Science and a minor in Statistics. Throughout his time at BYU he also participated as a Division One athlete playing linebacker for the BYU Men’s Football Team. Apart from school and athletics, he enjoys spending time outside participating in activities such as back country skiing, white water rafting, and hiking. He is passionate about solving problems and finding solutions and has spent time working at companies like UiPath and IDeA labs doing so. His career and education in computational data science has allowed him to take the hard skills of computation and apply them to real world problems everywhere. He hopes to continue to advance the field of analytics with these skills in the future whether it be in sports or any other industry.
Delma Nieves-Rivera
Delma Nieves-Rivera is a graduate student from the Computer Science department at Mississippi State University. She's pursuing a doctorate degree under the supervision of Dr. Christopher Archibald and Dr. Cindy Bethel. Her research interests include Artificial Intelligence, Game Theory, and Multi-Agent Systems.
Christopher Archibald
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.
David Grimsman
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.
Thinking the GOAT: Imitating Tennis Styles
Short Abstract:
Understanding how tennis players make decisions and the real-world implications of decision is key to designing competitive strategies. Increasing amounts of ball and player tracking data enable deeper analysis and in this paper, we develop a model to imitate players and learn the individual styles of players without the need for adaptation. We demonstrate the quantitative performance and qualitative insights our model can achieve with the flexibility of our approach.
Author(s):
Padmanaba Srinivasan
Padmanaba Srinivasan is a PhD student at Imperial College London, advised by Professor William Knottenbelt. He is interested in Computer Vision and Reinforcement Learning and their applications to sports. He received a Master of Engineering degree at Imperial College studying Electronic and Information Engineering and is a fan of tennis.
Raghavan Subramanian
Raghavan is Associate Vice President at Infosys and Head of the Infosys Tennis Platform. Raghavan has over 28 years of work experience in which he has led multiple strategic initiatives in marketing, Internal IT and R&D. He has advised organizations like the World Economic Forum, Australian Open, Roland Garros, ATP, International Tennis Hall of Fame, Madison Square Garden, Dow Jones, Bloomberg and Financial Times on their digital transformation initiatives. Raghavan holds a Bachelor’s degree in Electronics & Communication. He was adjudged the “Technology champion of Infosys” in 2006.
William Knottenbelt
William Knottenbelt is Professor of Applied Quantitative Analysis, Director of Industrial Liaison, and Director of the Centre for Cryptocurrency Research and Engineering in the Department of Computing at Imperial College London, where he became a Lecturer in 2000. He has co-authored more than 200 scientific papers, is an editor of Performance Evaluation Journal, and has served as general or program chair of numerous conferences and workshops related to quantitative modelling and/or cryptocurrencies. A keen supporter of student-led innovation, he is technical advisor to a number of start ups including Deep Render, Aventus and Deep Search Labs.
Robust Daily Fantasy Sports: Maximizing Reward via the Robust Optimization Paradigm
Short Abstract:
In daily fantasy sports, it may not always be the goal to maximize projected points on average. This paper proposes the use of the robust optimization paradigm to maximize rewards in 50/50 fantasy football competitions where contestants who score enough points receive the same payout. The final robust formulation is as tractable and interpretable as the standard mixed integer linear programming formulation, while outperforming the MILP formulation under some circumstances
Author(s):
Dubem Mbeledogu
Dubem Mbeledogu is a consultant with Bain & Company. Prior to Bain, he worked as a process design engineer for ExxonMobil designing refineries and chemical plants. Dubem’s main interests lie in normalizing the use of interpretable optimization and operations research as supplemental tools in decision-making processes, however he also has interest in interpretable data science more broadly. Dubem holds a bachelor’s degree in chemical engineering from Purdue University and an MBA with focus on Business Analytics from the MIT Sloan School of Management.
Estimating Positional Plus-Minus in the NBA
Short Abstract:
Plus-minus is a popular performance metric in sports. Our study follows the plus-minus framework and adopts a hierarchical Bayesian linear model to estimate plus-minus at the position level in the NBA from 2015-16 to 2021-22. This paper also uses redefined seven offensive and three defensive positions in the analysis, since traditional basketball player positions may not truly reflect player roles on the court. Overall, our analysis offers valuable information regarding average positional values in the NBA as well as the overall trend of player efficiency at various offensive and defensive positions.
Author(s):
Hua Gong
Hua Gong is an Assistant Professor in the Department of Sport Management at Rice Univeristy. Gong received his Ph.D. in sport and entertainment management from the University of South Carolina. His research interests include sport managemnet, sports analytics, and sports economics. In his spare time, Gong enjoys running and playing basketball.
Su Chen
Su Chen is an Assistant Teaching Professor of Data to Knowledge Lab at Rice University. She received her Ph.D. in the Department of Statistics and Data Science at the University of Texas at Austin. She earned her B.S. in Mathematics and her M.S. in Mathematics with a focus in Actuarial Science. Chen is an Associate of Society of Actuaries and has experience working in an actuarial consulting firm. Her doctoral research lies in the intersection of methodology, theory and computation of Bayesian statistics and their applications to high dimensional data analysis. She has experience developing and teaching both lower and upper division undergraduate courses in math, statistics and data science at UT-Austin and Texas A&M University prior joining Rice.
Explainable Defense Coverage Classification in NFL Games using Deep Neural Networks
Short Abstract:
Coverage scheme is at the core of understanding and analyzing any football defensive strategies. However, manual identification of the coverages is time-consuming and laborious. This paper presents a deep neural network model that classifies the coverages automatically and accurately. In addition, we tackle the opaqueness of the deep learning model through comprehensive model explanations using play embedding analysis and gradient-based approaches. The model explanations provide confidence that the model aligns with human experts' understanding, help speed up visual review processes, and bring additional insights about defense coverage schemes.
Author(s):
Huan Song
Huan Song is an applied scientist at Amazon Machine Learning Solutions Lab. His research interests are graph neural networks, computer vision, time series analysis, and their industrial applications. He obtained a PhD from Arizona State University and worked as a research scientist at Bosch Research North America. Outside of work, he enjoys exploring the beautiful nature.
Mohamad Al Jazaery
Mohamad Al Jazaery is an applied scientist at Amazon ML Solutions Lab. He helps AWS customers identify and build ML solutions to address their business challenges in areas such as logistics, personalization and recommendations, computer vision, fraud prevention, forecasting and supply chain optimization. Prior to AWS, he obtained his MCS from West Virginia University and worked as computer vision researcher at Midea. Outside of work, he enjoys soccer and video games.
Haibo Ding
Haibo Ding is a senior applied scientist at Amazon Machine Learning Solutions Lab. He is broadly interested in Deep Learning and Natural Language Processing. His research focuses on developing new explainable machine learning models, with the goal of making them more efficient and trustworthy for real-world problems. He obtained his Ph.D. from University of Utah and worked as a senior research scientist at Bosch Research North America before joining Amazon. Apart from work, he enjoys hiking, running, and spending time with his family.
Lin Lee Cheong
Lin Lee Cheong is an applied science manager with the Amazon ML Solutions Lab team at AWS. She works with strategic AWS customers to explore and apply artificial intelligence and machine learning to discover new insights and solve complex problems. She received her Ph.D. from Massachusetts Institute of Technology. Outside of work, she enjoys reading and hiking.
Kyeong Hoon (Jonathan) Jung
Jonathan is a Senior Software Engineer at the National Football League. He has been with the Next Gen Stats team for the last seven years helping to build out the platform from streaming the raw data, building out microservices to process the data, to building API's that exposes the processed data. He has collaborated with the Amazon Machine Learning Solutions Lab in providing clean data for them to work with as well as providing domain knowledge about the data itself. Outside of work, he enjoys cycling in Los Angeles and hiking in the Sierras.
Mike Band
Mike is a Senior Manager of Research and Analytics for Next Gen Stats at the National Football League. Since joining the team in 2018, he has been responsible for ideation, development, and communication of key stats and insights derived from player-tracking data for fans, NFL broadcast partners, and the 32 clubs alike. Mike brings a wealth of knowledge and experience to the team with a master's degree in analytics from the University of Chicago, a bachelor's degree in sport management from the University of Florida, and experience in both the scouting department of the Minnesota Vikings and the recruiting department of Florida Gator Football.
Michael Chi
Michael is a Senior Director of Technology overseeing Next Gen Stats and Data Engineering at the National Football League. He has a degree in Mathematics and Computer Science from the University of Illinois at Urbana Champaign. Michael first joined the NFL in 2007 and has primarily focused on technology and platforms for football statistics. In his spare time, he enjoys spending time with his family outdoors.
Thompson Bliss
Thompson Bliss is a Manager, Football Operations, Data Scientist at the National Football League. He started at the NFL in February 2020 as a Data Scientist and was promoted to his current role in December 2021. He completed his master’s degree in Data Science at Columbia University in the City of New York in December 2019. He received a Bachelor of Science in Physics and Astronomy with minors in Mathematics and Computer Science at University of Wisconsin - Madison in 2018.
Learning Contextual Event Embeddings to Predict Player Performance in the MLB
Short Abstract:
This paper leverages recent advances in deep learning (DL) to contextualize events that occur on the baseball diamond. Similar to how large language models such as the popular ChatGPT learn to understand language as a sequence of words, we train a model to understand the game of baseball as a sequence of pitches. We then use this understanding of the game to make predictions about how players will perform in the future based on their previous performances. Using only 10 games worth of pitch-by-pitch data, we can make predictions for single-game pitcher strikeouts and binary batter has-hit predictions that are competitive with three major sportsbooks in the US.
Author(s):
Connor Heaton
Connor Heaton is a Ph.D. Candidate in Informatics at the Pennsylvania State University, continuing at the university after he earned his B.S. in Computational Data Science in 2019. His research interests include deep learning, sports analytics, natural language processing, representation learning, and big data. Although his work focuses on the software side of computing, he also has a personal interest in computer hardware. A Pittsburgh native, he is a fan of the Steelers, Penguins, and Pirates.
Prasenjit Mitra
Prasenjit Mitra is a professor of Information Sciences and Technology at The Pennsylvania State University and a guest professor at L3S Center, Leibniz University of Hannover. He obtained his Ph.D. in Electrical Engineering from Stanford University in 2004, an M.S. in Computer Science from The University of Texas at Austin in 1994, and a B.Tech.(Hons.) in Computer Science and Engineering from the Indian Institute of Technology, Kharagpur in 1993. His research interests are in the areas of artificial intelligence, big data analytics, applied machine learning, natural language processing, and visual analytics. His research has been funded by the NSF CAREER award and by several grants from the DoD, DoE, DHS, NGA, DTRA, Microsoft Corp., Dow, Lockheed Martin, Raytheon, etc.
A Graph Neural Network deep-dive into successful counterattacks
Short Abstract:
The purpose of this research is to build gender-specific, first-of-their-kind Graph Neural Networks to model the likelihood of a counterattack being successful and uncover what factors make them successful in both men's and women's professional soccer. We demonstrate that gender-specific Graph Neural Networks outperform architecturally identical gender-ambiguous models in predicting the successful outcome of counterattacks using smaller sample sizes. And we show, using Permutation Feature Importance, which features have the highest impact on model performance.
Author(s):
Amod Sahasrabudhe
Amod Sahasrabudhe (24) is in his final year of his Master in Artificial Intelligence at Northeastern University, Boston. He completed his undergraduate degree in Information Technology in Pune University, India. The presented research was part of his 6-month co-op in the U.S. Soccer Federation during the 2nd part of 2022. He is an avid reader and a soccer enthusiast.
Joris Bekkers
Joris Bekkers (33) has 6 years’ experience working professionally in soccer analytics. He has been working as a data scientist and, most recently, as sports analytics engineer with the U.S. Soccer Federation since 2018. His career in soccer analytics started with a successful entry into the SSAC 2017 research paper competition with a paper titled “Flow motifs in soccer: What can passing behavior tell us?”. He is very excited to be back in Boston after 6 years for a second time!

2023 Poster Presenters

Fair and Efficient Ranking in Incomplete Tournaments
Short Abstract:
I discuss basic desirable fairness standards for the case of ranking teams in incomplete tournaments. I present a parsimonious family of scoring methods that uniquely satisfies these standards. It includes the win percentage method as a special case. I analyze this family of scoring methods in terms of efficiency, defined as how close a scoring method comes to capturing what the teams’ win percentages would have been, in a complete tournament. I show that efficient scoring methods are typically unfair. Finally, using data on betting odds, I calibrate the family of scoring methods to match, as closely as possible, the actual rankings that were used to determine the teams that would go on to compete for the championship of the NCAA division 1 football tournament between 2011 and 2017. I find that the rankings used by the NCAA were generally efficient and unfair, and I quantify the biases present in each year’s ranking.
Author(s):
Fernando Leiva Bertran
Fernando Leiva Bertran is an economics professor at Arizona State University. He obtained his PhD in economics at the University of Rochester, NY in 2004. His main areas of research are the economics of Innovation, with specific applications to patent policy, and the study of networks, with specific applications to patent citations (in the field of innovation) and incomplete tournament scoring methods (in the field of sports economics). Originally from Argentina, he obtained his College degree at the Universidad de San Andres, Buenos Aires in 1999. There, he was the captain of the university’s soccer team. He was also one of the two co-founders of the university’s “Math and Soccer” club. The club managed to increase membership by 50% in four years (from two to three members). Not to be discouraged, he continued playing soccer at the semi-amateur side “Rochester Italia” while simultaneously pursuing his PhD in economics. To this day, he has been unable to shake off either of his two passions.
Mining football players' behavioral profile: identifying candidate proxy features from event data.
Short Abstract:
This paper details how we modeled normative contextual pressure from event data. In our theoretical conceptualization of the problem, we introduced the reader to the Transactional Model of Stress and Coping (Lazarus & Folkman, 1984) and Brasen et al. (2019) modeling of stress. Building upon such contributions, we used several statistical learning approaches (supervised and unsupervised) to explore how normative contextual pressure affects soccer performance. We finished with a use-case in which we used a simple cluster technique (K-NN) to find natural groups of players with disparate performing profiles for low, medium, and high-pressure situations.
Author(s):
Luis Meireles
He joined Portuguese soccer giants FC Porto in 2008, and since then, he has worked as a Psychologist for the youth and professional squads. Meanwhile, he finished his Ph.D. in Applied Psychology in 2019 at the University of Minho – Portugal. He earned a Master’s Degree in Data Science and Engineering at the Faculty of Engineering, University of Porto, in 2022. His interests are creating new psychological performance metrics from the available data types (i.e., event, tracking, pose estimation, text) using present-day algorithms and computational powers to target and develop talent.
Tiago Mendes-Neves
Tiago Mendes-Neves is a Ph.D. Student at the Faculty of Engineering, University of Porto. His research interests are the intersection between soccer and artificial intelligence. Specifically, he focuses on using data to develop soccer players to their fullest potential.
João Mendes-Moreira
He is an associate professor at the Faculty of Engineering, University of Porto, and a researcher at INESC TEC. He is a co-author of 1 book, 22 journal papers, and 59 conference papers, among other publications. He supervised 1 Ph.D. student and co-supervised 1 Ph.D. student, supervised 69 MSc students, and co-supervised 7 MSc students. Currently, he supervises 8 Ph.D. students and 2 MSc students and co-supervises 6 Ph.D. students and 1 MSc student. He is the director of the Master in Data Science and Engineering at the Faculty of Engineering, University of Porto.
Player Tracking Facilitates Valid Causal Inference: The Average Treatment Effect of Defender Proximity on Scoring
Short Abstract:
Defense is important in basketball, but how much does defender proximity actually CAUSE a player to miss a shot? The goal of this current work is to show within a Causal Inference framework how valid causal conclusions can be made from high-dimensional player tracking data in basketball. We demonstrate and quantify the interactive causal effect of defender proximity and shot distance from the hoop on probability of success. While much focus has recently been on prediction modeling in sport, we postulate that Causal Inference is likely to have a higher return-on-investment when it comes to enhancing athlete and team performance.
Author(s):
Matthew S. Tenan
Matt Tenan is the Program Director for Human Performance & Data Science at the Rockefeller Neuroscience Institute. With a background in Athletic Training (B.S. Ithaca College), Exercise Physiology (M.A. University of North Carolina-Chapel Hill), Neuroscience (Ph.D. University of Texas-Austin), and Statistics (Fellowship at University of Texas-Austin), Matt brings a unique perspective on modeling human performance from the league-level down to the cellular-level. Having worked in both Army R&D and medical data science, his focus is constantly on delivering data products which enhance performance and mitigate injury. Matt serves as an Editor for two preeminent journals in the field of human performance: Sports Medicine and the Journal of Strength & Conditioning Research. As a Tar Heel Born and Bred, he is willing to root for anyone but Duke.
Ali R. Rezai
Ali Rezai MD is a neurosurgeon whose career has been dedicated to advancing the care of people with neurological and mental health conditions. Dr. Rezai is the Associate Dean of Neuroscience at West Virginia University (WVU) and Executive Chair and Director of the WVU Rockefeller Neuroscience Institute. Author of over 200 scientific publications, including Nature, JAMA Neurology, Lancet Neurology, and PNAS, Dr. Rezai has served on the editorial board of multiple scientific journals. Dr. Rezai has been the Principal/Co-investigator on seven NIH grants. He is a sought-after speaker at medical conferences as well as popular tech venues including Collision, SXSW, TED and Web Summit. Dr. Rezai was invited to present his research to the President of the United States as well as to members of the US Senate and House of Representatives on Capitol Hill, and four State Governors.
cricWAR: A reproducible system for evaluating player performance in limited-overs cricket
Short Abstract:
This paper presents a comprehensive framework and a novel set of metrics for player evaluation in limited-overs cricket. Due to the rise of T20 cricket leagues, there is significant interest in comprehensive statistics that capture the net value an individual player adds, and traditional cricket stats fall short of that goal. Inspired by sabermetrics, we develop metrics such as run value, runs above average (RAA), value over replacement player (VORP), and wins above replacement (WAR) for batters and bowlers in limited-overs cricket. These metrics are calculated using ball-by-ball data readily available through the R package cricketdata, co-developed by us. We assess the uncertainty in RAA and WAR estimates through a resampling approach. Finally, we discuss the reliability of these metrics and comment on the possible implications of this work for the T20 teams.
Author(s):
Hassan Rafique
Hassan Rafique is an Assistant Professor in the Department of Mathematical Sciences and founding Director of the Center for Data Science at the University of Indianapolis. His research work has been at the intersection of optimization and machine learning. In addition, he is particularly interested in sports analytics, data for social good, and data visualization. Outside work, he enjoys being outdoors, playing and watching cricket, and letting his new favorite sport, American football, consume his Sundays.
Correcting for preferential bias in NFL fourth-down decision making
Short Abstract:
When estimating the probability of a successful fourth down the data we use are conditional on teams attempting to go-for-it. We expect better teams to go-for-it more often in a given situation, and worse teams to be put in must-go situations more often. Correlation between the decision to go-for-it and the outcome can lead to biased probability estimates when the decision mechanism is not accounted for. To correct for this we treat it as a missing data problem, fitting a generalized Heckman selection model to all fourth-down plays from the 2014-2021 NFL seasons. We find a positive correlation between the decision to go-for-it and success probability when there are multiple viable choices for teams, and a negative correlation when teams are forced to go-for-it by the game situation. This causes fourth down probabilities estimated using only plays where teams go-for-it to be biased high in fourth-and-short scenarios, and biased low in fourth-and-long scenarios.
Author(s):
Daniel Daly-Grafstein
I'm a PhD student in statistics at the University of British Columbia. My research focuses on Bayesian methods for causal inference, with applications in healthcare and sports. Previously, I completed my MSc in statistics at Simon Fraser University and worked as a soccer data analyst at Sportlogiq.
Reconstruction of Trajectories of Athletes Using Computer Vision Models and Kinetic Analysis
Short Abstract:
Athlete’s pose acquisition and analysis is promising to provide coaches with details of athletes performance and thus help to improve athletes’ performances with more detailed supervision from coaches. Compared with traditional ways of acquiring an athlete's gesture, such as using wearable sensors, computer vision technology has advantages of low-cost, high-efficient and non-intrusive. This paper aims to bridge these two fields, by reconstructing athletes’ trajectory using monocular (i.e. single-camera-shot) videos. Under a few assumptions that are applicable to most of the sports of athletics, we proposed a method combining computer vision techniques and physics laws to reconstruct athletes’ trajectories from monocular videos.
Author(s):
Qi Gan
Qi Gan is a PhD candidate of informatics at Télécom Paris of the Polytechnic Institute of Paris. His research interests include computer vision and sports analytics. His current research project aims to extract high accurate human pose trajectory from videos of athletes or patients, and to extract features from the pose trajectory to help analyze athletes’ performance or patients’ rehabilitation progress. His major interest in sports is basketball and he has been a fan of LeBron James since 2003.
Sao Mai Nguyen
Sao Mai Nguyen specializes in cognitive developmental learning, reinforcement learning, imitation learning, automatic curriculum learning for robots : she develops algorithms for robots to learn multi-task control by designing themselves their curriculum and by active imitation learning. She received her PhD from Inria in 2013 in computer science, for her machine learning algorithms combining reinforcement learning and active imitation learning for interactive and multi-task learning. She holds an Engineer degree from Ecole Polytechnique, France and a master's degree in adaptive machine systems from Osaka University, Japan. She has coordinated project KERAAL to enable a robot to coach physical rehabilitation. She is currently an assistant professor at Ensta IP Paris, France and was previously with IMT Atlantique. She also acts as an associate editor of the journal IEEE TCDS and IJRR, and is the co-chair of the Task force "Action and Perception" of the IEEE Technical Committee on Cognitive and Developmental Systems. For more information visit her webpage: https://nguyensmai.free.fr.
Stephan Clémençon
Stephan Clémençon carries out his research in applied mathematics in the LTCI laboratory of Télécom Paris. He leads the S2A research team (Statistics and Applications). His research themes are mainly in the fields of statistical learning, probability and statistics. He is responsible for the “Big Data” Specialized Masters at Télécom Paris. He held the “ Machine Learning for Big Data ” industrial chair from 2013 to 2018 and is now actively involved in the “ Data Science and AI for Digitalized Industry and Services ” chair.
Eric Fenaux
Mouvement is life. I graduated as an aerospace engineer in 1983 (ISAE Sup’Aéro). I got various experiences at AIRBUS (fly by wire) in Formula one (aerodynamics) and at STELLANTIS where I was in charge of active safety (definition of metrics to assess car behaviour, including ADAS performances). From 2015 to 2019 I was convenor at ISO fto define test procedures to assess ADAS performances. In 2020 I was certified for AI at TELECOM PARIS and was a research engineer in 2021.As an independent researcher, I work with automotive industry and sport coaches to improve training techniques with AI.In 2022 I was appointed as an AI expert by the French mintery of research.
Mounim A. El-Yacoubi
Mounim A. El-Yacoubi (Member, IEEE) received the Ph.D. degree from the University of Rennes, France, in 1996. He was with the Service de Recherche Technique de la Poste (SRTP), France, from 1992 to 1996. He was a Visiting Scientist with the Centre for Pattern Recognition and Machine Intelligence (CENPARMI), Montreal, Canada, and an Associate Professor with the Catholic University of Parana, Curitiba, Brazil, from 1998 to 2000. From 2001 to 2008, he was a Senior Software Engineer at Parascript, Boulder, Colorado. At SRTP and Parascript, he has developed handwriting recognition software for real-life automatic mail sorting, bank check reading, and form processing. Since June 2008, he has been a Professor at Telecom SudParis, Institut Polytechnique de Paris. His research interests include artificial intelligence, data science, machine learning, modeling human user data, especially behavioral signals like handwriting, voice, gesture and activity recognition, biometrics, e-health, smart agriculture, and smart cities. His favorite sports are soccer, tennis and track and field, and favorite teams are FC Barcelona, Machester City and PSG. (Based on document published on 3 June 2022).
Ons Jelassi
Ons Jelassi is lecturer and researcher at Télécom Paris (Institut Polytechnique de Paris) in the Team Signal, Statistique et Apprentissage (S2A) of the Information Processing and Communication Laboratory (LTCI). She’s also head of Télécom Paris Executive Education. Her current research bridges the domains of distributed computing and statistical analysis of large scale data. It aims to construct algorithms and systems for developing scalable, robust and sustainable learning machines that solve real-life problems.
Competitive Balance in Professional Sports: A Multidimensional Perspective
Short Abstract:
Competitive balance is a contentious issue in professional sports to a large extent because there remains general disagreement on what constitutes a competitive league. We address this issue using a simple framework that encapsulates multiple viewpoints on competitive balance and argue that this unified perspective is essential for understanding how league policies shape competitive landscapes. Using this novel framework, we demonstrate how important structural shifts in the ability of teams to capture talent at below-market wages have influenced competitive balance over the longer run. Finally, we provide examples of rules that counterbalance the adverse incentives that can arise in these situations.
Author(s):
Levi Bognar
Levi Bognar is a Research Assistant at the Federal Reserve Bank of Chicago. His research has appeared in multiple Chicago Fed outlets including Chicago Fed Insights and the Midwestern Economy Blog. Prior to this position, he received his B.A. in Economics with Honors from the University of Notre Dame in 2021. He enjoys exercising, reading, and is an avid follower of Notre Dame athletics.
Scott A. Brave
Scott A. Brave is the head of economic analytics for decision intelligence company Morning Consult; and was previously a senior economist at the Federal Reserve Bank of Chicago where his responsibilities included the releases for the Chicago Fed's economic and financial activity indexes. He received his B.A. from the University of Chicago in Economics with Honors and an M.B.A. from the Booth School of Business. His research has appeared in journals such as the Journal of Sports Economics, Journal of Sports Analytics, International Journal of Forecasting, and International Journal of Central Banking. When he is not helping to wrangle up his five children, he spends his free time slavishly following the Chicago Cubs and Blackhawks.
R. Andrew Butters
R. Andrew Butters is an Assistant Professor in the Business Economics & Public Policy department at the Kelley School of Business at Indiana University. Prior to joining Kelley, he was an Associate Economist in the Economic Research department at the Federal Reserve Bank of Chicago. His research has appeared in journals, such as American Economic Review, American Economic Journal: Microeconomics, and the Journal of Sports Analytics. He received his B.A. from the University of North Carolina at Chapel Hill, and his Ph.D. from the Kellogg School of Management at Northwestern University. When he’s not cooking or on the golf course, he enjoys watching any Chicago sports team.
Kevin A. Roberts
Kevin A. Roberts is a PhD Candidate in Economics at Duke University. Previously, he received his B.A. from Davidson College and worked as an Associate Economist at the Federal Reserve Bank of Chicago. His research employs causal inference methods to study labor market institutions and policy. His work on the economics of sports has appeared in the Journal of Sports Economics and the Journal of Sports Analytics and has served as a welcome reprieve from supporting various mediocre sports franchises.

Research Paper Finalists

Abstract Submissions for SSAC24

Please submit your abstract below for SSAC24
Max file size 10MB.
Uploading...
fileuploaded.jpg
Upload failed. Max size for files is 10 MB.
Thank you!
Your submission has been received!
Oops! Something went wrong while submitting the form.
Max file size 10MB.
Uploading...
fileuploaded.jpg
Upload failed. Max size for files is 10 MB.
Thank you!
Your submission has been received!
Oops! Something went wrong while submitting the form.

Open Source Competition - Voting

Review our SSAC 2022 open source finalists below and cast your vote for your favorite submission HERE!

2022 Open Source Finalists

Understanding why shooters shoot - An AI-powered engine for basketball performance profiling
Short Abstract:
In professional basketball, it is crucial for the coaching staff of a team to analyze an opposing team and develop an effective strategy. Understanding player shooting profiles is an essential part of this analysis: knowing where certain opposing players like to shoot from can help coaches neutralize offensive gameplans from their opponents, while understanding where their players are most comfortable can lead them to developing more effective offensive strategies. We present a tool that can visualize player performance profiles in a timely manner while taking into account factors such as play-style and game dynamics, generating interpretable heatmaps that allow us to identify and analyze how these non-spatial factors affect the performance profiles. Our methods provide an effective and efficient tool that can provide insight into how certain players and teams play, without requiring the time-consuming process of reviewing hours of film, and could potentially be applied to other sports with adaptations.
GitHub Link (Open Source)
Author(s):

Alejandro Rodriguez Pascal, Ishan Mehta, Muhammad Khan, Rose Yu, Frank Rodriz

Learning from the Pros: Extracting Professional Goalkeeper Technique from Broadcast Footage
Short Abstract:
As an amateur goalkeeper playing grassroots soccer, who better to learn from than top professional goalkeepers? In this paper, we harness computer vision and machine learning models to appraise the save technique of professionals in a way those at lower levels can learn from. We train an unsupervised machine learning model using 3D body pose data extracted from broadcast footage to learn professional goalkeeper technique. Then, an “expected saves” model is developed, from which we can identify the optimal goalkeeper technique in different match contexts.
GitHub Link (Open Source)
Author(s):

Matthew Wear, Ryan Beal, Tim Matthews, Gopal Ramchurn, Tim Norman

Winning duels in VALORANT, a visualization of optimal positioning
Short Abstract:
This paper applies traditional sports analytics metrics with novel machine learning models in a brand new competitive Esport. By leveraging in-game positional data, we are able to evaluate the difficulty of a particular gun fight and assign a win probability to both sides. We use these predictions to identify players who are performing above or below expected, and identify strengths and weaknesses for NRG’s player development. We are hopeful for more analytics in Esports from current working professionals and the younger generation.
GitHub Link (Open Source)
Author(s):

DeMars DeRover

Using Machine Learning to Describe how Players Impact the Game in the MLB
Short Abstract:
This paper draws upon recent advances in Natural Language Processing (NLP) and Computer Vision (CV) to learn to describe the way in which players impact the game in the MLB. In particular, this work views the game as a sequence of events - instead of a set of summary statistics describing said events - and trains machine learning models to describe the impact that a given sequence of events has on the game. The models describe a sequence of events for a single player over a relatively small time period; so we refer to the model output as player form embeddings - descriptions of how they have impacted the game in the short term. We demonstrate how these embeddings can be used to describe players over the short- and long-term, and contain signals useful for predicting the outcome of games.
GitHub Link (Open Source)
Author(s):

Connor Heaton, Prasenjit Mitra