Data in Sports Analytics

For most of football’s history, much of what we watched on the field went unmeasured. Today, nearly every player and ball movement throughout the game is measured, modeled, and analyzed in real time. This data is improving fan experiences and giving them richer sport insights. It's also changing how professionals approach the game—from improving player safety to unlocking new training environments. The results speak for themselves: a 35% reduction in lower-extremity injuries from the redesigned kickoff format, informed by Next Gen Stats data. Innovations like completion probability and rush yards over expectation that make broadcasts more engaging. And now, pose-tracking technology that captures full skeletal data 60 times per second, is opening doors to VR training that could accelerate player development from years to months. I'm proud of how we've expanded our partnership with the NFL on Next Gen Stats, powered by AI tools like Amazon SageMaker and Amazon Quick. What started as a tracking experiment in 2015 has become a critical part of the NFL’s infrastructure that uses machine learning models on AWS to process data from 22 players, generating 500-1,000 stats per play, instantly. What a win for the Hawks last night! If you're still riding the excitement, take a few minutes to read through this deep dive into the science that powers the complex stats you see on screen throughout the season. Cool look at the history of our partnership with the NFL through Next Gen Stats! https://lnkd.in/gX8Mpe7T

Here’s my major prediction for the professional sports industry next year.   By the end of 2026, artificial intelligence will no longer be a fringe experiment in sports – it will be a foundational layer powering the industry’s growth, on and off the field. Any organization still relying on gut feel, spreadsheets, and siloed data will be structurally behind in both revenue and relevance.   It’s not just about performance. The integration of AI is reshaping every part of the sports business — from fan engagement and ticketing to media, commercial operations and player health. This is key to unlocking a new era of scalable value creation, sustaining the growth we’ve seen in recent decades.   AI is already bending the curve, and the growth potential looks a lot like a hockey stick:   💲 Spend is exploding: The global “AI in sports” market, estimated at nearly $9B in 2024, is forecast to reach $28B by 2030, a 21%+ CAGR. That’s not a side bet; it’s a signal of where leaders and operators see future value.   ⚕️ Performance & health are moving first: Teams working with specialized platforms have reported material outcomes. One AI system forecasts ~75% of potential athlete injury risks inside a seven-day window. Another is helping Major League Soccer teams cut total injuries by ~28% and reduce the salary paid to unavailable players by ~30% (equating to millions of dollars a season). Those are direct P&L and asset-protection gains, not just “innovation theatre”.   📣 Fan experience is being rewired in real time: The NBA’s work with Microsoft and AWS, for example, is pushing AI into games broadcasts: instant narrative-building, multilingual recaps, “Inside the Game” analytics feeds, and new experiences across apps, social media and even inside the stadium/arena. Formula 1 is also turning 1.1 million data points per second per car into predictive race insights and storytelling for a global audience.   By 2026, the true outliers won’t be the AI pioneers, they’ll be the organizations that failed to adapt. Here’s what’s becoming table stakes:   – A robust AI layer across ticketing, pricing, media, sponsorship, and performance – A single, integrated data spine replacing fragmented systems – The skills, talent, and culture to deploy AI tools with the same fluency as playbooks and scouting reports   The road to AI-based optimization won’t be clean. There will be bad models, governance clashes, and cultural pushbacks. But positive transformation never happens in straight lines. It requires bold experimentation. The difference now is that AI’s upside can be quantified in revenue growth, commercial yield and fan lifetime value.   As AI capabilities are adapted across the sports value chain, the industry’s ability to continue growing its overall value could accelerate dramatically.   #BigIdeas2026 – here on LinkedIn.

Google Cloud is announcing an industry-first, AI athlete performance tool prototyped with U.S. Ski & Snowboard (USSS). Built by Google Cloud engineers, the tool was tested by U.S. Olympians ahead of the Winter Olympic Games to understand their high-performance needs. Using our full-stack AI, we are enabling athletes to train with better safety, more confidence and greater precision than ever before. Here’s what makes it unique:  - 3D Analysis: Our AI leverages spatial intelligence to "see" through bulky winter gear, mapping an athlete’s 3D skeletal points using only standard video—no sensors or wearable suits required. - Near Real-Time Physics: Using custom Google Cloud TPUs, Gemini reasoning engines, and research from Google DeepMind, we deliver complex biomechanical insights—like angular velocity and airtime—in near real-time. - Conversational Insights: Using the multimodal power of Gemini, coaches can interact with data using natural language. - Safety & Resilience: By identifying subtle biomechanical patterns, we can help coaches mitigate injury risks before they happen. Read more on our blog: https://lnkd.in/g9Fu2Ckd

>> 𝗔𝗜’𝘀 𝗡𝗲𝘄 𝗣𝗹𝗮𝘆𝗶𝗻𝗴 𝗙𝗶𝗲𝗹𝗱 𝗪𝗵𝗮𝘁 𝗔𝗪𝗦 re:Invent 2025 𝗿𝗲𝘃𝗲𝗮𝗹𝗲𝗱 𝗮𝗯𝗼𝘂𝘁 𝘁𝗵𝗲 𝗳𝘂𝘁𝘂𝗿𝗲 𝗼𝗳 𝗯𝘂𝘀𝗶𝗻𝗲𝘀𝘀 I joined Amazon Web Services (AWS) re:Invent 2025 in Las Vegas. Here’s the quiet truth most people missed 👇 The National Basketball Association (NBA), National Football League (NFL), Formula 1, PGA TOUR, and the Bundesliga International GmbH are already building the AI blueprint every business will copy next. Across every stage, demo, and interview, one pattern was impossible to ignore: AI isn’t just helping athletes win. It’s rewriting decision making, performance, and personalization. And business leaders should be paying very close attention. 🏀 𝗧𝗵𝗲 𝗡𝗕𝗔: 𝗦𝗲𝗲𝗶𝗻𝗴 𝘁𝗵𝗲 𝗜𝗻𝘃𝗶𝘀𝗶𝗯𝗹𝗲 The NBA unveiled Gravity, an AI metric tracking 29 data points at 60 frames per second to measure how much attention a player draws even without the ball. Invisible influence becomes measurable insight. Business lesson: The biggest drivers of outcomes are often the ones you are not tracking yet. 🏎️ 𝗙𝗼𝗿𝗺𝘂𝗹𝗮 𝟭: 𝟭.𝟯% 𝗼𝗿 𝗡𝗼𝘁𝗵𝗶𝗻𝗴 AWS simulations helped redesign F1 cars to reduce downforce loss from 50% to 15%, enabling closer racing. As Ruth Buscombe put it: 1.3% separates champions from last place. Business lesson: Micro advantages compound. Precision beats scale. 🏈 𝗧𝗵𝗲 𝗡𝗙𝗟: 𝗥𝗲𝗮𝗹 𝗧𝗶𝗺𝗲 𝗗𝗲𝗰𝗶𝘀𝗶𝗼𝗻𝘀 The NFL’s Next Gen Stats processes 500M+ data points per season, powering real time predictions and reinventing plays like kickoffs. Business lesson: Stop using data to explain yesterday. Start using it to shape the next move. ⛳ 𝗧𝗵𝗲 𝗣𝗚𝗔 𝗧𝗢𝗨𝗥: 𝗗𝗮𝘁𝗮 𝘁𝗵𝗮𝘁 𝗙𝗲𝗲𝗹𝘀 One swing creates 70 million data points. But as Ken Lovell explained, value only appears when data makes people feel something. Business lesson: Numbers alone do not persuade. Stories do. ⚽ 𝗧𝗵𝗲 𝗕𝘂𝗻𝗱𝗲𝘀𝗹𝗶𝗴𝗮: 𝗣𝗲𝗿𝘀𝗼𝗻𝗮𝗹𝗶𝘇𝗶𝗻𝗴 𝗖𝗼𝗻𝘁𝗲𝘅𝘁 Luccas Roznowicz explained the Bundesliga’s Data Story Finder adapts commentary and emotional tone in real time, based on why fans care. Business lesson: AI doesn’t just scale content. It scales understanding. 📘 𝗧𝗵𝗲 𝗕𝘂𝘀𝗶𝗻𝗲𝘀𝘀 𝗣𝗹𝗮𝘆𝗯𝗼𝗼𝗸 𝗘𝗺𝗲𝗿𝗴𝗶𝗻𝗴 Across leagues, the next era of enterprise AI is already visible: • Personalization at scale • Real time beats size • Agentic AI that acts within guardrails • Data only matters when it connects emotionally Sports are showing what’s next. AI doesn’t replace people. It sharpens instincts, accelerates feedback, and transforms experience. If stadiums are the new AI labs, the question for leaders is simple 👇 Are you watching the game or playing it? ---- 👉 Love my content? ☑ Follow me on LinkedIn: https://lnkd.in/gjUQk7HF 👉 Found this helpful? Share it! ♻️

Manchester City Football Club's appointment of Paul Power as Head of AI is another signal of where elite football is heading. Clubs have invested heavily in data for years. What is changing now is how that data gets used. This role is not about collecting more information. It is about improving decision-making across the club. AI has the potential to impact multiple areas: • Recruitment, through faster and deeper player analysis • Performance, through better prediction and planning • Medical, through injury risk profiling and load management • Operations, through automation and efficiency The key point is integration. Data only creates value when it shapes decisions. Without clear application, it remains noise. Manchester City Football Club's model has always focused on marginal gains. This appointment shows a move towards scaling those gains through technology. It also raises a wider question for the game. Do clubs have the structure and leadership to make use of AI effectively? Hiring a Head of AI is one step. Aligning that function with recruitment, performance, and coaching is where the real advantage sits. Find out more about the appointment by following the link to Training Ground Guru's article in the comment section.

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.

🚀 Scouting Talent with AI 🚀 At IBM #Think2024, I learned about an incredible partnership between IBM and Spain's Sevilla FC. Built on IBM's watsonx platform, Scout Advisor leverages advanced NLP to understand and utilize the specific language of football (soccer) scouts. ⚽️ Scout Advisor transforms how Sevilla FC manages its massive database of player reports, providing a user-friendly interface that translates natural language searches into actionable insights. This tool significantly reduces the time spent on paperwork, allowing scouts to focus on what they do best—evaluating talent and making informed decisions. As Victor Orta, Sevilla FC Sporting Director, puts it: "We are never going to sign a player with data alone, but we will never do it without resorting to them either." With Scout Advisor, Sevilla FC can now harness the full potential of their scouting reports, combining expert observations with data-driven insights for a more effective recruitment process. Learn more about how IBM's watsonx is revolutionizing sports recruitment: https://ibm.biz/BdmKHy #IBMpartner #Think2024 #AI #SportsTech #Futbol #SevillaFC #DataScience

🚨 University of Arizona Football | Performance Systems Overview (2022–2023) During the 2022–2023 season, we had the opportunity to build out a truly integrated performance system at Arizona — blending objective monitoring, individualized training, and collaborative decision-making to support player development and availability. Here’s what that looked like behind the scenes: 🔧 System Components – Developed a centralized Athlete Management System (AMS) – Integrated force plate CMJs on GD-2 and GD+1 – Mapped GPS data to every drill in practice by volume, intensity, and density – Built a stoplight readiness model (Red/Yellow/Green) based on force, asymmetry, and wellness inputs – Weekly 1080 Sprint profiling to target individual acceleration deficits and monitor trends 📊 In-Season Monitoring Strategy – Combined neuromuscular data (jump height, RSImod, asymmetry) with GPS and workload trends – Used CV% and SD thresholds to flag meaningful fatigue changes – Adjusted pre-practice prep, lifting intensities, and recovery based on G+1/G-2 trends – Created individual and positional reports shared daily with performance and coaching staff 📈 Results – Logged 31 new top speed records – Saw a 35% reduction in soft tissue injuries with minimal hamstring-related time-loss – Aligned training with the competitive calendar: Winter → Spring → Camp → Season → Postseason – Worked closely with the Performance Director to manage daily decisions around practice structure and player availability 🎯 Takeaway What made the difference wasn’t any one piece of tech or protocol — it was the ability to tie together force diagnostics, GPS load, sprint data, and on-field context into a unified decision-making system. Building that bridge between data and action is where the real impact happens. #SportsScience #AthleteMonitoring #PerformanceAnalytics #SpeedDevelopment #InjuryPrevention #CollegeFootball #ForcePlates #GPS #1080Sprint #SpellmanPerformance #ArizonaFootball

🎾 Breakthrough in my AI-Powered Padel Analytics After months of intensive development, I'm thrilled to share a major milestone in my AI-powered padel analytics project! This latest iteration showcases how we can analyze amateur padel games through cutting-edge computer vision. 💻 What you're seeing on screen 1. Backbone inference pipeline using open-source models: 1.1 Player detection and tracking using a custom tracker specifically optimized for padel which mixes kalman filter with re-identification 1.2. Player pose estimation 1.3. Ball detection 2. Upstream inference pipeline using custom transformer based time series models 2.1 Ball state classification 2.1.1 🔴 Floor bounces 2.1.2 🔵 Player hits 2.1.3 🟢 Wall bounces 2.1.4 ⚫ Net 2.2. Player stroke classification 2.3 Rally classification 🚀 Lightning-Fast Performance The entire inference pipeline runs at 70 FPS on an RTX 3090 – that's 2.3x real-time speed. 📊 Rich Data Collection 1. Player position and velocity in real-world coordinates 2. Distance covered during play 3. Time spent in strategic zones (back court, net, or transition) 4. Team attribution 5. Top view ball projections in real world coordinates As in previous iterations, court keypoints enable homography projection of player positions onto a 2D court representation for comprehensive analysis. 💡 Latest Innovations 1. Enhanced Court Mapping: Each ball state now has its own 2D court projection for deeper tactical insights 2. Smoother Tracking: Custom smoother algorithms eliminate position jitter for cleaner data I truly believe that this kind of scentific advancements can make professional-grade insights accessible for amateur players, democratizing the sport. The combination of real-time processing power and comprehensive data collection opens up exciting possibilities for player development and tactical analysis. What applications do you see for this technology in sports training and performance analysis? Alessandro Ferrari Ultralytics Piotr Skalski Roboflow Nicolai Nielsen #deeplearning #computervision #sportstech #sportsanalytics #padel