Programs
People starting out, or coming from another field, who want the foundations in both working languages before choosing a specialism.
No job is guaranteed. We do not promise placement, an interview, or an offer.
If none of these are familiar, this is probably not the right program, and the call will tell you that faster than the page will.
This is a real session, not a promotional cut. Modeling and App Development runs live alongside the program.
Each phase names the skills you work on, what exists at the end of it, and what you can do by then.
Start where most job postings start, on data you actually care about.
Load a season of data, clean it, and answer a question about it that nobody handed you the answer to.
The second language, because sports analytics runs on both and picking a side this early is a mistake.
Work in whichever of the two languages the task actually suits, and say why you chose it.
Turning coursework into the one thing a reader will actually open.
Show someone your work and explain what you would do differently if you started it again.
Not sure which phase you would start from? That is the first thing the call works out.
Ask about this programEvery one of these is drawn from a model you write yourself, on data you choose. Scroll and they build themselves, which is roughly what it feels like the first time your own one works.
Pick your sport. The methods are the same underneath: a model, honest evaluation, and a chart that makes one point. The sport is what makes you care enough to finish it.
Located pitches with break tails, plus horizontal against induced vertical break by pitch type.
Velocities and break values are illustrative, in the ranges these pitch types actually live in. No real pitcher, team or game.
Expected points per shot over a half court, with a five-touch possession drawn on top.
Shot volumes and percentages are illustrative. The shape is the real argument: a corner three beats a long two on value, not on vibes.
Open-play xG as a logistic in goal angle and log distance, under a passing network sized by touches.
Positions, touch counts and pass volumes are illustrative. Pitch and penalty-area dimensions are the real ones.
Routes drawn at real depths off the line, beside a win probability line across one drive.
The drive and its probabilities are invented. Route depths are the ones these routes are actually run at.
Two-sigma dispersion ellipses from a bivariate normal, the same object as a golfer's shot cone.
Landing-point means, spreads and shares are illustrative. Court and service-box dimensions are the real ones.
A sprint model integrated in the browser: force, a falling top speed, and drag, with 100 meter splits read off the curve.
An illustrative runner, not a real performance. The split pattern is the one a well-run 400 produces.
Each one is on sale on its own, as a recording you buy once, on its own page. The program is the order, the weekly work around them and the capstone at the end.
Async masterclass · 75 min
What Fills the Seats
Greg MatthewsPhD · Director, Center for Data Science and Consulting @ Loyola University Chicago
After this you can fit ridge, lasso and elastic net on the same data, tune them honestly, and pick the one that generalizes.
Async masterclass · 75 min
FILL THE GAPS
The Injury Report Problem
Greg MatthewsPhD · Director, Center for Data Science and Consulting @ Loyola University Chicago
After this you can run a complete multiple-imputation workflow on a sports dataset full of holes and pool the results correctly.
Course · 66 lessons
PYTHON FROM PUCK DROP
FoundationZ of Data Science
Evan Callaghan
After this you can load a season of data in Python, clean it, and answer a question nobody handed you the answer to.
Course · 56 lessons
ZERO TO DRAFT DAY
BreeZing Through the Tidyverse
Paul SabinPhD · Co-Founder @ Sage Sports Group
After this you can turn raw NFL, NBA or MLB data into an R report that reruns and gives the same answer.
AI coaching is built into the practice sessions. The coach takes the stakeholder's part, and you work the problem in whatever medium the question actually calls for.
AI as copilot, not autopilot. You learn to direct the machine and defend the output. The scarce part is not producing an answer; it is knowing whether the answer is right and being able to say why in a room that will push back.
How it actually runs, and the kind of question it runs on.
Practice is timed. You get a real task and a clock, not a quiz. The session is recorded, and the review afterwards is about the reasoning you showed rather than whether you reached the expected answer.
Scenarios are written the way the question actually arrivesNo job is guaranteed. We do not promise placement, an interview, or an offer. What the program promises is the work: a capstone you can defend, a portfolio with real builds in it, and interview practice that is recorded and reviewed.
There is no public price and no checkout on this page. Cost, dates and where you would start are settled on a short call, and the honest answer is sometimes that a single session or course is the better start.
That is the first thing the call works out. The plan on this page is the whole route; a person who already has the foundations starts further along it.
Then take the method and leave the sport. Cleaning real data, answering one question honestly and explaining it to someone who does not code is the foundation. It is the first thing you do in any of these fields:
Simulated technical interviews, recorded and reviewed. Front-office presentation practice, where a recommendation meets a room that pushes back. AI orchestration: planning work for delegation, delegated builds, and the checks that catch what a model got wrong.
Modeling and App Development is the live track running alongside the program, so the weekly sessions and the plan pull in the same direction.
There is no public price and no checkout on this page. A short call settles cost, dates and where you would start, and if a single session is the better start we will say so.
No job is guaranteed. We do not promise placement, an interview, or an offer.
Ask about this programFirst name and email. One message when a session recording, a skill, a cheat sheet or a posting worth your time arrives here, and no other mail. Replies reach a person.