Data in Sports Analytics

This isn’t just an AI demo. It’s live. And it's what the future of every customer interaction could look like. Every year, the Masters feels like a tradition frozen in time. But behind the scenes, it's a glimpse of the future. This year, over 20,000 golf shots at Augusta National are captured, analyzed, and narrated by AI, within minutes. Not just stat lines, but real insights, like: 🟢 “Shots from this location have an 82% chance of birdie.” 🟠 “Hole 14 is playing the toughest today, with 25% bogeys.” 🔮 “No. 9 is projected to be the third most difficult hole today.” That’s Hole Insights 2.0, built on watsonx and tuned on 180,000+ historical shots and expert input, including past Masters caddies. AI narration returns in English and Spanish, now also available through the Masters app on Apple Vision Pro, complete with 3D course views and multi-stream live play. It’s easy to dismiss this as "just sports tech." But I see something bigger here. This is what happens when AI is tuned, grounded, and embedded into a real-world experience: - Real-time context - Predictive intelligence - Multimodal delivery (text, voice, AR) - Personalization at scale For any business leader thinking about AI transformation: don’t just look at dashboards and copilots. Look at how we partnered with the Masters to turn data into decisions, and decisions into experiences. AI is not a plug-in. Allows full reinvention.

On Saturday, the Oakland Ballers became the first pro sports team to let AI manage in-game decision-making. AI set the lineup, decided when to pull pitchers, when to use pinch hitters, and how to position the defense. The experiment offers useful lessons for all organizations: 𝗨𝘀𝗲 𝗔𝗜 𝘁𝗼 𝘁𝗮𝗰𝗸𝗹𝗲 𝗼𝘃𝗲𝗿𝗹𝗼𝗮𝗱: The Ballers turned to AI, in part, because the data had outgrown human capacity. Every pitch, matchup, and defensive shift produces more signals than a manager can possibly process in real time. AI’s biggest value isn’t surfacing more information. It’s in parsing complexity so leaders can act with speed and confidence. And the advantage compounds: it’s rarely one big decision that wins the game (or transforms a business), but hundreds of small ones made swiftly and correctly. 𝗕𝗲 𝗱𝗲𝗹𝗶𝗯𝗲𝗿𝗮𝘁𝗲 𝗮𝗯𝗼𝘂𝘁 𝘁𝗵𝗲 𝗱𝗶𝘃𝗶𝘀𝗶𝗼𝗻 𝗼𝗳 𝗹𝗮𝗯𝗼𝗿: The Ballers set clear roles for humans and AI. AI handled the data-heavy calls (lineups, pitching changes, defensive shifts), while humans kept the split-second judgments, like third-base coaching or waving runners home. Manager Aaron Miles also had override authority. 𝗢𝗿𝗴𝗮𝗻𝗶𝘇𝗮𝘁𝗶𝗼𝗻𝘀 𝗻𝗲𝗲𝗱 𝘁𝗵𝗲 𝘀𝗮𝗺𝗲 𝗶𝗻𝘁𝗲𝗻𝘁𝗶𝗼𝗻𝗮𝗹𝗶𝘁𝘆: decide where AI should automate, where it should augment, and what should remain exclusively human. And always design the system so a human can step in to override. 𝗖𝗼𝗻𝘀𝗶𝗱𝗲𝗿 𝗻𝗲𝘄 𝗺𝗲𝗮𝘀𝘂𝗿𝗲𝘀 𝗼𝗳 𝘀𝘂𝗰𝗰𝗲𝘀𝘀: When the Ballers brought AI into the game, they weren’t just watching the scoreboard. They wanted to understand how AI’s decisions compared to a human manager’s, and what could be learned from the differences. Measuring AI performance isn’t just about whether the outcome was successful; it’s about the counterfactual: did the machine’s call actually beat the decision a human would have made? Congratulations to the Ballers for pioneering this experiment—and for winning the game to boot.

🧠 🎾 Smarter tennis, savvier fans 👏 🙌 For over three decades, IBM has partnered with the (USTA) United States Tennis Association to transform the US Open into a cutting‑edge digital experience—engaging 14 million+ global fans through the official app and website. Key pillars of the innovation: ☁️ Hybrid Cloud: A flexible, scalable multicloud infrastructure via Red Hat OpenShift enables the USTA to handle traffic surges exceeding 5,000%, while keeping apps agile and resilient 🔢 Data & watsonx.data: Capturing over 7 million data points per tournament—from serve speed to shot placement—plus 20+ years of historical records and media. Centralizing it all in a hybrid data lakehouse fuels real‑time AI insights. 🧐 AI (watsonx.ai / Granite / Orchestrate): Empowering content creators with tools that summarize matches, generate commentary, and craft rich narratives. Example: Match Reports jumped from 20 to 64 in just the first round of 2024—a 300% productivity boost IBM+8 👀 Automation & Observability: Tools like IBM Instana, Terraform, and Apptio deliver near-perfect stability—99.999% uptime, 80% reduction in provisioning cycle time, and optimized cloud cost management IBM Latest innovations powered by watsonx (2025): 🎾 AI‑generated commentary with audio & captions on video highlights, using AI trained on match stats, rankings, and linguistic nuance 🎾 Match Insights include the Power Index, blending structured stats and sentiment analysis, plus AI Draw Analysis, which ranks how "favorable" each player's draw is and updates as the tournament advances ❓ Why this matters: By blending hybrid cloud, AI, data, and automation, IBM and the USTA aren't just reporting scores—they're crafting immersive, dynamic, and personalized fan experiences. As the tournament scales, innovation scales with it. This is a prime example of enterprise AI in action: strategic, scalable, and fan-first! https://lnkd.in/eb98QSmE #AI #watsonx #USOpen #FanExperience #IBMConsulting #DigitalInnovation

Robots won't be playing pro sports (at least not for a few more years!) but, honestly, what is our thumbnail designer supposed to do? Today's episode *is* all about how A.I. is transforming baseball ⚾️ (with lessons for all industries) BASEBALL'S DATA REVOLUTION • Baseball's analytical journey evolved from the "Moneyball" era of the early 2000s to today's A.I.-powered decision making. • Every Major League Baseball (MLB) team now employs data scientists, treating analytics as a competitive necessity. • MLB's Statcast system generates 7 terabytes of data per game, tracking everything from pitch spin rates to fielder movements. • Machine learning (MLB ML?? 😂) algorithms excel at finding patterns in this mountain of information that humans would miss. SCOUTING & PLAYER DEVELOPMENT • Modern scouting uses ML models to analyze vast arrays of player data beyond traditional stats. • Models analyze nuanced metrics like exit velocity, launch angle, and spin rates to make more accurate performance projections. • Teams can identify undervalued players by recognizing patterns that traditional scouting might miss. • Player development has become personalized through A.I. systems that analyze individual strengths and weaknesses. • A.I. can flag mechanical issues in swings or pitching motions before they become major problems. GAME STRATEGY • Managers now use predictive analytics to inform game decisions, from pitching changes to defensive positioning. • A.I. models simulate countless scenarios to recommend optimal strategies for specific matchups. • Defensive shifts evolved through deep learning analysis of where every ball lands. • Teams blend human intuition with machine predictions, using technology as a "high-tech co-pilot". • Players and coaches regularly consult iPads mid-game to study the latest analytics. FAN EXPERIENCE • A.I. now enriches broadcasts with real-time "win probability" graphs and advanced metrics like "catch probability". • Advanced statistics help fans gain deeper appreciation of player skills and game dynamics. • MLB's Automated Ball-Strike system ("robo-umpire") uses AI and vision technology to ensure consistent, fair calls. LESSONS FOR EVERY BUSINESS • If baseball—deeply rooted in tradition—can embrace A.I., any industry can be transformed by a data-driven approach. • Organizations that blend domain expertise with A.I. insights outperform competitors. • Early adopters gain significant advantages until others catch up. • A.I. augments human strategic decision-making rather than fully replacing it (like the robots... this will be true for at least a few more years!). • Success comes from experimenting with data, trusting analytics, and maintaining an open mind to change. You can hear more on the above in the most recent episode (#874) of the "Super Data Science Podcast with Jon Krohn" on any podcasting platform and YouTube. Link in comments ⬇️ #superdatascience #ai #aiinsports #machinelearning #baseball #sports

Amazon Prime Video is embarking on its second NFL season as the exclusive broadcaster of Thursday Night Football, introducing a suite of AI-powered features to immerse viewers in the strategic intricacies of the game. By training machine learning models on thousands of plays, Amazon was able to generate graphics that highlight open receivers, predict potential blitzes, and calculate field goal probabilities using predictive analytics. Amazon is clearly leveraging its position to amplify TNF promotions across its ecommerce platform. The company says that the Black Friday game (in particular) will include heavy holiday integrations, reflecting Amazon’s ambition to intertwine its core business with entertainment properties like TNF. On the technical front, viewers with compatible devices can enjoy the enhancements of HDR streaming. However, the absence of 4K video seems cruel and unusual as it’s impossible to purchase a set with HDR that is not also 4K. While TNF is currently the focal point, the advancements tested here could easily find their way to Premier League and other Amazon sports broadcasts. Speaking as a football fan, it’s super fun to see how Amazon and the NFL are using data to create richer fan experiences. 'Amazon Enhances TNF with AI and Data' #AI #ArtificialIntelligence #Amazon #NFL #4k

My view on baseball for the past 58 years - boorrrriiinnnggg. Then, while on vacation with friends recently, my buddy Jim got me to watch the Datacast broadcast. Seven windows of real-time data analytics? - yes, please! I had never even heard of this before, but for the League Championship Series and the World Series, MLB ran a simulcast version with some absolutely incredible real time data analyses, visualizations, and predictive analytics. I did some additional research on the techniques and technologies that they used for this version, and I was completely mesmerized watching this level of data firepower applied in a popular broadcast. The whole system is built on Google Cloud infrastructure. Here are some of the main components: 🔸 3D Pose Tracking - Tracks 18 points on each player's body - Captures 30 images per sensor per second - Processes 540 images per player per second4 - Enables creation of immersive 3D game views similar to video games 🔸 Data Processing Infrastructure - Anthos for on-premises Kubernetes processing at ballparks - BigQuery for real-time query results - Bigtable for managing large workloads - Cloud SQL Postgres for rapid data replication 🔸 AI Modeling and Analysis - Processes ≈15 million data points per game - Custom neural networks for pitch classification - Predictive modeling for catch probability - Base stealing success rate analysis - Real-time ball and strike analysis Needless to say, I am now a big baseball fan - at least this version of baseball. 😁 Did anyone else catch these telecasts? What did you think? #baseball #datacast #sportsanalytics #datavisualization #ai

The National Football League (NFL)'s commitment to player safety and performance has reached new heights with the groundbreaking Digital Athlete program, an innovative AI-powered initiative that’s redefining how teams train and protect players. Working alongside Amazon Web Services (AWS) and sports science experts, the NFL has built a virtual platform that creates a digital avatar for each player, enabling coaches and health professionals to monitor, predict, and optimize player health and performance. With real-time data at their fingertips, teams can anticipate injury risks and fine-tune player workloads, keeping athletes in peak condition and extending their careers. Ben Peterson, VP of Health and Performance for the San Francisco 49ers, has leveraged AI to revolutionize team management strategies, running millions of simulations to assess potential impacts on players. AI-driven adjustments have allowed coaches to prevent injuries, as shown when the system flagged a quarterback's mechanics as potentially problematic, leading to minor tweaks that improved both accuracy and safety. By freeing up valuable time for coaches and trainers to engage directly with players, AI has strengthened communication and boosted on-field performance for the 49ers. Jeff Miller VP of Player Health and Safety, notes that the proactive use of AI is making the game smarter and safer. The Digital Athlete program’s predictive analytics detect early warning signs, enabling prompt interventions that could avert serious injuries. The initiative is setting a new industry standard in sports safety, offering a blueprint for how AI can be adopted by other sports to improve player well-being and performance. The NFL's Digital Athlete program is a true testament to how technology can drive positive change. Dive into this journey of innovation by reading the full article — click the link to explore how AI is shaping the future of sports! https://lnkd.in/ex7qBUng

In 2022, the NFL paid nearly $800 MILLION to injured players. But in 2024, they used AI to crunch 6.4 million data points—per game. And it’s slashing injuries by 29%. Here’s how it’s saving careers (and championships): As a former NFL agent and Wall Street vet, I've seen data transform sports. The physical toll is brutal, but the NFL's latest innovation changes everything. They're using AI to predict injuries before they happen. But here's what makes this revolutionary: The system processes 8TB of video weekly through computer vision. ML models analyze every tackle, cut, and sprint in real-time. AI runs 4.3M simulations per game to spot injury risks. It's trained on 10,000+ simulated seasons. The tech behind it? Mind-blowing: Players wear Zebra Tech sensors tracking: • Location in real-time • Speed variations • Impact forces • Distance covered • Acceleration patterns But the magic happens in the cloud: AWS processes data within 12 seconds. The system builds a "Digital Athlete" - your virtual twin. It uses 3D pose estimation for biomechanical analysis. This predicts injuries with unprecedented accuracy. Here's where it gets fascinating: Mouthguards capture data at 20,000 Hz, measuring: • Force of collision • Direction of impact • Velocity at contact When risks exceed thresholds, something remarkable happens: Teams get instant tablet alerts. These aren't generic warnings. Each alert considers: • Player's injury history • Position benchmarks • Current game demands The impact? Staggering: The Chiefs now average 3.2 proactive subs per game based on AI. These aren't random switches. They're data-driven decisions revolutionizing player management. And here's the biggest breakthrough: The system flags players hitting: • 85% of position-specific speeds • 90th percentile contact forces • 15+ high-intensity impacts But there's an irony in all this: While the NFL develops this amazing tech, they keep pushing for an 18-game season. They're using AI to protect players while adding more wear and tear. It's like installing airbags while removing seatbelts. From my NFL experience, I know what's at stake. This isn't just about preventing injuries. It's about extending careers and protecting legacies. Keeping our favorite players on the field longer. Football's future isn't just player safety. AI drives smarter decisions in: • Player management • Performance data • Injury prevention This tech changes how we analyze the game.