BASKETBALL AI
Welcome Readers,
In this this edition, we let AI run wild a bit on a legend NBA player and peek at how the new 76ers lineup causes problems for opponents.
We’ll take a look at some leadership analytics to make the case why it may be time for the WNBA Commish to go and explore the evolution of gut feeling to advanced analytics for coaches.
And…we just dropped a new Guide on how to create a coaching staff in ChatGPT.
In this issue:
Most UNSTOPPABLE 76ers Lineup in History!
“Pistol” Pete Recreated in AI… And He BROKE the NBA!
Evolution of Basketball Analytics: From Gut Feelings to AI
Analytics of Failed Leadership: Why WNBA Commish Must Go
New Guide: Build 5 AI Coaches Inside One ChatGPT Project
Let’g Go
LINEUP ANALYSIS
😕 Most UNSTOPPABLE 76ers Lineup in History!
Overview: The Philadelphia 76ers’ new lineup anchored by LeBron James and Jaylen Brown alongside dynamic rookie V.J. Edgecombe, floor spacing forward Dean Wade, Joel Embiid and Tyrese Maxey presents a match up nightmare for opposing teams.
By combining generational court vision with dynamic athleticism, elite floor balance, and interior dominance, Philadelphia will force opponents to make defensive trade offs on nearly every possession.
Details: Here Are 3 Top Tactical Problems for Opponents
Elite Gravity and Unmatched Weak Side Playmaking: LeBron James serves as the ultimate high volume orchestrator alongside Tyrese Maxey’s explosive downhill threat. Double teaming Joel Embiid becomes untenable. Any secondary help directed toward the post triggers high value skip passes to LeBron or Jaylen Brown. Meanwhile, V.J. Edgecombe acts as an athletic transition engine, punishing aggressive crashing on the offensive glass by turning live ball turnovers into immediate 2-on-1 fast breaks.
Optimal Shot Quality Generation & Floor Balance: Brown and James create relentless rim pressure that forces defense rotations, while Dean Wade functions as an ideal high efficiency off ball connector. Wade’s elite corner three efficiency and quick decision making prevent help defenders from sagging off to clog Embiid’s operating space. The resulting spacing gives Philadelphia’s top options wide open driving lanes and maximum floor area to operate.
Switchable Perimeter Defense and Defensive Rating Ceiling: Defensively, pairing Brown and Edgecombe’s point-of-attack disruption with Embiid’s elite rim protection metrics saturates the floor. Wade’s positional flexibility allows Philadelphia to execute seamless 2 through 4 switching schemes without compromising defensive rebounding. Opposing offensive sets running heavy pick-and-roll action will struggle to hunt mismatches or pull Philadelphia’s rim protector away from the paint.
Why It Matters: By surrounding generational talents with elite complement players like Edgecombe and Wade, Philadelphia eliminates classic roster vulnerabilities. Opponents can no longer rely on standard defensive coverage schemes or targeted match up hunting. To neutralize this lineup, coaching staffs will have to construct entirely new defensive game plans.
LEGEND ANALYSIS
👀 Recreating “Pistol” Pete with AI… And He BROKE the NBA!
Overview: Analyzing "Pistol" Pete Maravich through the lens of modern AI tools is a fascinating exercise. In the 1970s, his game was often labeled as "showboating" or "reckless" by traditionalists.
If we fed his college and NBA footage into modern machine learning models, predictive engines, and computer vision systems, AI would identify him as a high efficiency, hyper advanced offensive engine born forty years too early.
Details:
1. Computer Vision & Biomechanical Tracking (The "Unconscious" Game)
Running Maravich's tape through modern optical tracking systems or pose estimation models, the spatial data flags him as a mechanical anomaly.
Decoupled Gaze Vectoring (The No-Look Pass): Computer vision models track a player’s "gaze vector" (head and eye orientation) relative to their passing trajectory. Standard guards have a high correlation between where they look and where they pass. AI would show that Maravich’s gaze and pass vectors frequently achieved a near 90-degree deflection angle, mathematically proving his elite ability to manipulate defensive help side rotations with his eyes.
Dribble Frequency and Pocket Control: By analyzing pixel-by-pixel coordinates of the ball, tracking AI would measure his "dribble-to-stride ratio." Under the incredibly strict "carrying" and "palming" rules of his era, Maravich kept his hand strictly on top of the ball while maintaining a high frequency, low-to-the-ground bounce. AI would classify his handle as "highly secure under tight constraint."
Kinematic Release Speed: Modern shot tracking AI measures the time from the dip of the ball to release. Maravich’s catch and shoot release time would rank in the elite percentiles, resembling modern quick release shooters.
2. Predictive Modeling & "Era Translation" (The Gravity Factor)
One of the most powerful uses of sports AI is running predictive simulations taking historical data and projecting how a player's style translates to different rules and environments.
The 3-Point Shot Chart Simulation: Maravich played his entire collegiate career (where he averaged an absurd 44.2 PPG) and almost his entire NBA career without a three point line. When LSU coach Dale Brown manually charted Pete's shots, he calculated that Maravich would have averaged around 57 PPG with a 3-point line. A generative spatial AI model, simulating his deep range accuracy, would project a massive spike in his True Shooting Percentage (TS\%) and overall offensive rating on a modern spaced floor.
Gravity Mapping: AI calculates "defensive gravity", how tightly defenders must cling to a player off the ball. Because Maravich was a threat to pull up from 30 feet, AI simulations would show him creating "maximum gravity," pulling defenders way past the perimeter and opening massive passing lanes for his teammates.
3. Natural Language Processing & Semantic Clustering (The Playstyle Label)
If you asked a Large Language Model (LLM) or a semantic clustering algorithm to analyze descriptions of Pete's playstyle and group him with modern counterparts, it would skip the standard 1970s guards entirely.
Instead of clustering him with his peers, NLP and semantic models would map his skill-signature to a hybrid cluster of modern superstars:
AI Clustering Node | Shared Skill Characteristic |
Stephen Curry | Off-the-dribble deep shooting, continuous off-ball movement, and transition green-light confidence. |
Kyrie Irving | High-variance, creative ball-handling angles and improvisational pocket dribbles. |
Steve Nash / Jason Williams | High-velocity, flashy transition playmaking (behind-the-back, elbow passes) designed to reward rim-runners. |
AI Summary Diagnostic: Pete Maravich was an "optimal variance creator." In an era that valued rigid, low risk half court execution, his high tempo, high risk playmaking was structurally ahead of its time. Today's analytics engines would demand he play exactly the way he did with a green light to shoot from 30 feet.
ANALYTICS EVOLUTION
💹 Evolution of Basketball Analytics: From Gut Feelings to AI
Overview: For decades, professional basketball was governed almost entirely by intuition, traditional scouting, and basic box score stats like points and rebounds. Today, the game is driven by advanced spatial data and artificial intelligence. The transformation of basketball from an art based on "gut feel" to a quantitative science represents one of the most drastic shifts in modern sports history.
Details: When advanced analytics first emerged in the 2000s, front offices, scouts, and veteran coaches were notoriously slow to adopt them. Skee Ball style shot charts and efficiency metrics were frequently dismissed in favor of traditional "eye tests." However, as data proved that prioritizing three-pointers and layups over mid-range jumpers yielded a statistically superior point yield, the league shifted dramatically.
Today, basketball analytics has evolved far beyond basic efficiency charts into sophisticated computer vision and machine learning models:
Optical Tracking: Camera systems capture player and ball coordinates at high frame rates, measuring micro variables like defensive proximity, acceleration, and shot arc.
Contextual Metrics: AI models quantify previously intangible factors, such as off-ball gravity, passing vision, and defensive impact.
Predictive Playbook Design: Neural networks analyze thousands of hours of game footage to identify defensive coverage weaknesses and recommend optimal play calls.
Looking forward, the sport is heading toward real time automated tactical adjustments, where AI algorithms process live game data during timeouts to simulate opponent counters and suggest optimized lineup combinations.
Why It Matters: The integration of AI elevated basketball from an instinct driven game to a battle of optimized strategy. Front offices that leverage advanced modeling can better assess draft talent, manage player workload to prevent injuries, and execute precise game plans. In the modern NBA, statistical literacy is no longer an optional advantage. It is a fundamental requirement for competitive survival.
LEADERSHIP
🕛 Analytics of Leadership: Time for WNBA Commish To Go?
Overview: While the WNBA is experiencing unprecedented macro growth, a high performance organization must be judged on how its leadership manages internal health, relationships, and operational efficiency during a expansion cycle. The data driven and behavioral evidence suggests that Commissioner Cathy Engelbert’s leadership style has created structural friction that now threatens the league’s long term enterprise value and ability to scale.
A recent ESPN article pointed out that team officials, owners, players and agents across the league see Engelbert's style and approach as problematic, saying she often comes across as "not personable," "defensive," "dismissive," "condescending" or "out of touch."
Details: The Case for Leadership Change
1. The Behavioral Indicator: Evasion and Accountability
The recent incident at the American Century Golf Championship where Engelbert agreed to a national interview with Dan Patrick, canceled, and was then seen golfing nearby is not just a PR error; it is a critical behavioral indicator of leadership risk. For the chief executive of a major sports league during its highest growth phase to evade tough, public questions (specifically regarding officiating, expansion, and player safety) directly damages the league's public credibility. An athletic asset's value is deeply tied to the perception of integrity and executive courage; this incident represents a failure in both.
2. The Relationship Metric: The Trust Deficit (NPS)
The most severe indicator of organizational stress is the breakdown in labor management alignment. Players are the league's primary capital asset, and their sentiment matters. Key leaders within the WNBA Players Association (WNBPA) have publicly cited an alarming disconnect, referring to league leadership as "the worst in the world."
In corporate and executive analytics, Net Promoter Score (NPS) is a key metric traditionally used to measure customer loyalty, satisfaction, and advocacy. In this specific analysis, it was applied to Labor/Talent Sentiment (as a "Talent NPS" or "Player NPS") to quantify the internal trust, relationship health, and organizational alignment between the WNPA and league leadership.
In an industry built on talent buy in, the inability to maintain baseline organizational trust, a collapsing Net Promoter Score (NPS) from its own athletes represents a structural barrier to long term success.
3. The Operational Diagnostic: Reactive vs. Proactive Management
A diagnostic of the WNBA’s operations under current leadership reveals a pattern of low Capital Efficiency and reactive scaling. Historic market tailwinds are driving the league's success, yet the infrastructure has consistently lagged behind:
Lagging Infrastructure: Essential requirements, including full time charter travel and increased arena capacities to accommodate historic attendance, were only implemented after severe public pressure and player pushback, rather than being engineered into the 2024 growth strategy beforehand.
Officiating and Safety Process Failures: Continued controversy regarding game day discipline, officiating inconsistency, and risk control points to an underperforming competition oversight model.
NBA Commissioner Adam Silver had to directly intervene and override Engelberts’ decision not to issue a fine and suspension to Alyssa Thomas following a dangerous play involving Caitlin Clark. When a league’s chief executive refuses to act on a clear safety violation simply because a referee missed the initial call, it demonstrates a complete reliance on passive protocol over active leadership
Why Change Matters Now: High growth enterprises cannot afford reactive management. Holding onto legacy, risk averse leadership models during a generational explosion in popularity erodes brand equity and creates operational drag.
To capitalize on this unprecedented momentum, the WNBA needs an agile, operational leader who can immediately repair the trust deficit with players and proactively build the high performance infrastructure the league’s next era demands.
NEW GUIDE
🚨 Build 5 AI Coaches Inside One ChatGPT Project
Overview: Coaches…Imagine walking into your office and having FIVE expert coaches arguing over your biggest program decisions completely unfiltered!
In our latest Guide, Build a Coaching Staff Inside One ChatGPT Project, Dan Barto shows you how to build a full, interactive coaching staff inside ONE ChatGPT Project. Zero holding back, zero fake agreement and just pure, honest feedback!
Details and What You Will Create: Using context engineering, you feed ChatGPT your roster, playbook, and constraints. You construct five personas:
Offensive Coordinator: Obsessed with pace and space.
Defensive Coordinator: Demands half-court physical discipline.
Player Development Coach: Focuses on long-term growth.
Strength Coach: Tracks load, recovery, and movement quality.
Head Coach Synthesizer: Cuts through the debate to make the final call.
Why It Matters: Every human staff has blind spots. This AI roundtable stress tests your game plans, exposes hidden assumptions, and sharpens your meetings before you step on the court!
🔥 DON’T MAKE HIGH STAKES CALLS ALONE!
[DOWNLOAD THE FREE GUIDE BELOW] and build your ultimate AI decision room now!
🛠 Tools Spotlight:
Tools mentioned in this edition:
Sportsvisio - Record the game. We do the rest. Film from any device and get a full box score plus highlight clips for every player within 24 hours. No stat crew, no tagging.
Veo - Record basketball games without a camera operator and never miss those memorable three-pointers or dunks ever again.
Trace - The Best AI Camera to Record Basketball. Automatically capture and follow every shot on the court.
Basketball AI - Free website access to guides, tools, research, and more!
📰 Everything Else in Basketball AI:
SportsVisio published findings from over 59,000 shots captured across grassroots and youth leagues. Leveraging upgraded computer vision pipelines that run natively on consumer GPUs, the system now automatically categorizes players into distinct "Shot Signatures" (e.g., Three-and-Rim, Paint Punisher, Mid-Range Master, Spot-Up Specialist).
Why it matters: High school and club coaches no longer have to build custom player profile tags. The system automatically identifies a player’s primary offensive archetype directly from raw smartphone footage.
Veo rolled out a major software suite update for its Veo Cam 3 basketball users:
Conversational Coach Assist: An integrated conversational LLM assistant that lets coaches ask direct natural-language questions about their film (e.g., "Give me a 30-minute practice plan workflow based on our team's turnovers last night").
2D Radar Spacing: A spatial visualizer that maps floor positioning and player spacing in real time from panoramic 180° dual-4K video feeds.
Hardware-and-software provider Trace has stepped up its push into youth and travel circuits with TraceCam Basketball and AI Reels.
The system utilizes panoramic single-camera tracking to automatically edit individualized, player-specific highlight reels ("PlayerFocus").
Instead of requiring parents or assistants to hand-edit game film for college recruiting, the AI isolates every shot, rebound, and assist into individual shareable channels per player.
📆 Upcoming Conferences, Events and Latest Guides:
July 21, 2026 Last issue of Basketball AI
Latest Basketball Guides:
Conferences:
Sports Analytics and Data Visualization Conference (ICSADV): August 3-4, 2026, New York, NY
That’s a wrap for this edition. The next newsletter will be published Tuesday August 18, 2026.
Tell us what you thought of today's newsletter to help us improve it for you.
Until next time, Terry and Dan