Skip to the content.

Welcome to DSAI4Sports 2023!

We are excited to announce that DSAI4Sports workshop is joining force with KDD 2023 Entertainment, Sports and Media (ESM) Day. We will offer a platform to exchange research ideas, identify research opportunities and challenges in applying AI/ML for sports analytics, engage in thoughtful discussions, and foster the development of a research community centered around this field. Both DSAI4Sports workshop and the ESM Day will take place on Aug 7th and in same conference room.

Sports analytics combines advanced analytics, domain knowledge and computational methods on sports data to generate insights and deepen understanding into the various aspects of sports. This includes predicting most likely event outcomes, identifying optimal strategies, understanding individual and collective performance, estimating player potential, etc. These insights were traditionally achieved through carefully designed statistical methods. But with the recent creation and availability of large-scale datasets, breakthroughs and new understandings have been achieved via the application of AI/ML methods. This includes using sequence modeling to determine optimal path trajectories with real-time sensor data from players/equipment, applying computer vision models to game footage to capture important events, or training large language models to summarize large corpus of game-related commentaries.

In particular, generative AI (GAI) has emerged as a powerful tool for understanding and enhancing various aspects of sprots performance and strategy. By generating realistic data samples the closely resemble the characteristics of the original training data, GAI has found wide-ranging applications in various domains, including computer vision, natural language processing, and now, sports analytics. The opportunities that leverage GAI for sports analytics include and are not limited to: sport-specific foundational models, game scenarios simulation, automated play generation, natural language-based strategy optimization and sport narrative generation etc.

The DSAI4Sports workshop aims to bring together interested researchers and practitioners at the intersection of data science, GAI, ML and sports analytics.

Accepted Papers

Program Schedule

Time: Aug 7 (Monday), 2023. 8am - 5:30pm

Room: 101A

Time Domain Title Speaker(s)
8:00 - 8:10 Kickoff Exciting opportunities for AI in Sports, Media and Entertainment Special Day Chairs
8:10 - 9:00 Entertainment The Secrets of the Data Science Behind Hollywood’s Magic Adam Husein
9:00 - 9:50 Sports Next way of seeing sports Tracey Ho
9:50 - 10:10   Coffee Break  
10:10 - 11:00 Media Data science @ the New York Times Chris H. Wiggins
11:00 - 12:00 Panel AI Opportunities in Sports, Media and Entertainment Adam Husein, Tracey Ho, Chris H. Wiggins
13:30 - 14:00 Sports To be added Mike Band
14:00 - 14:30 Sports When Data Meets Reality Augmenting Sports Scenes with Visualizations Zhutian (Zhu-Tian) Chen
14:30 - 15:00 Sports To be added Phil Martin
15:00 - 15:20 Sports Paper Presentation: Beep: Balancing Effectiveness and Efficiency when Finding Multivariate Patterns in Racket Sports To be added
15:20 - 15:40 Sports Paper Presentation: The CoachAI Badminton Environment: Improving Badminton Player Tactics with A Novel Reinforcement Learning Environment To be added
15:40 - 16:00 Sports Paper Presentation: RallyGraph: Specialized Graph Encoding for Enhanced Volleyball Prediction To be added
16:00 - 16:45 Panel Sports Panel Discussion Mike Band, Zhutian (Zhu-Tian) Chen, Phil Martin
16:45 - 17:30 Sports GenAI for Sports Workshop Henry Wang

Invited Speakers

Mike Band

Mike Band 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.

Zhutian Chen

Zhutian (Zhu-Tian) Chen is an incoming Assistant Professor of Computer Science at the University of Minnesota-Twin Cities and is currently a PostDoc Fellow in the Visual Computing Group at Harvard University. His research interests lie at the intersection of Data Visualization, Human-Computer Interaction, and Augmented / Virtual Reality (AR/VR). He is particularly interested in the potential of AR/VR technologies to enhance sports experiences. He has developed human-AI systems designed to enable users to visualize data within AR/VR sports scenes through natural interactions such as touch, speech, and gaze. His innovative work has been recognized and published in top-tier venues including IEEE VIS, ACM CHI, and TVCG, and has received a best paper award from ACM CHI and three best paper honorable mention awards from IEEE VIS.

Zhutian Chen

Phil Martin serves as the VP of Data Products and ML Strategy at FOX Corporation. During his six-year tenure at FOX, Phil has spearheaded the creation of several products that utilize FOX’s vast data sets to boost fan engagement across all platforms. Most notably, Phil’s team recently launched “Catch Up TV with Highlights,” which utilizes the AWS machine learning framework and models to provide autonomous recaps to viewers who tune in mid-broadcast for events such as Men’s World Cup 2023, MLB 2023 season, and USFL 2023 season. Phil is responsible for the creation of FOX’s contextual ad engine, optimized regional programming and forecaster, as well as the “Foresight” which enables live production to utilize real-time and historical sports data to effortlessly convey situational and relevant stories. Phil’s passion for product development and advanced solutions, along with his love for sports, drives him to continuously improve FOX’s linear and digital properties, making them the premier destination for sports content engagement.

Call For Papers

The core topic of the workshop is on Data Science, AI, and ML-based approaches for sports analytics, covering a broad range of sports activities like football, soccer, volleyball, badminton, tennis, basketball, golf, table tennis, hockey, car racing, swimming, and e-sports. We invite papers that demonstrate AI/ML use cases in the following broad (potentially overlapping) categories:

The DS/AI/ML methods that address the above use cases span generative AI, spatial-temporal data modeling, time-series analysis, computer vision, explainable AI, reinforcement learning, natural language processing, multi-modal learning and others. We welcome both industrial and academic papers submissions.

The submission to the workshop must be in maximum length of 4 pages, excluding references. Papers must be submitted in PDF format, and formatted according to the Standard ACM Conference Proceedings Style. The review process is double-blind, and author names and affiliations should NOT be listed. Papers will be evaluated on, but not necessarily limited to, the novelty, validity, and application impact. Accepted papers will be presented as posters during the workshop and listed on this website (non-archival/without proceedings). A small number of accepted papers will be selected to present during the workshop as contributed talks.

Please visit this link for your submission.

Any questions may be directed to the workshop email address:

Key Dates

Workshop Organizers

Huan Song Panpan Xu Lin Lee Cheong Henry Wang
Huan Song Panpan Xu Lin Lee Cheong Henry Wang


We thank the program committee for the help in workshop organization and paper reviews: