Learn Data Science Through Real Projects

Where to start

Four doors, one building.

Everything below runs on the same live rooms and the same practitioners. The difference is what you are trying to get to.

Where you are now

Staying current while shipping

Masterclass

Live sessions every week across six tracks, with the recording, the code, and the environment included.

See the Masterclass

Breaking into analytics

Career Programs

A week-by-week game plan: skills, deliverables, mentor sessions, and a capstone you can defend.

See the programs

Levelling up a team

Partnerships

Put a research team, a department, or an agency on current content with dedicated live instruction.

Talk to us

You need it built

Consulting

The people who teach this also build it. AI orchestration, modeling, applications.

Book a delivery call

AthlyticZ Worlds

The practice happens between the sessions.

Worlds is the part that is hardest to describe and easiest to recognize once you see it. A live room teaches the method; this is where you use it enough times that it becomes yours.

AthlyticZ WorldsA practice world worked through end to end.

Interactive practice worlds built from each course's own code, data and recordings. Every quantity computed live from the source data, every instructor quotation verified against the recording, and no exercise published unless its reference solution runs and passes its own tests.

Built from the course's own code and data, not a generic exercise set
Quantities computed live from the source, so a number on screen is the number in the data
Nothing published until its reference solution runs and passes its tests

From the catalog

Pick the thing you want to be able to do.

Bundle Build Bayesian Models in Sports Becoming a BayeZian From first principles to the specialist models teams hire for. StanRGaussian processes

Scott Spencer, PhDTeaches applied Bayesian modeling See the course → Course Build LLM Tools That Get Evaluated SynergiZing ML and LLMs in R A tidymodels pipeline, a retrieval pipeline, a deployed API and a chat interface. RtidymodelsRAG

Nic Crane, PhDTeaches LLM-powered tooling in R See the course → Bundle Build Apps a Front Office Opens Daily The Complete Shiny Engineering Stack Modular architecture, custom components, mobile, and a real deployment. RShinyJavaScript

Veerle Eeftink-van LeemputTeaches production Shiny engineering See the course → Course Build Machine Learning Pipelines Python MachineZ scikit-learn end to end, with evaluation honest enough to survive review. Pythonscikit-learnGAMs

Patrick McFarlaneTeaches predictive modeling on sports data See the course → Bundle Build Bayesian Models in Sports Becoming a BayeZian From first principles to the specialist models teams hire for. StanRGaussian processes

Scott Spencer, PhDTeaches applied Bayesian modeling See the course → Course Build LLM Tools That Get Evaluated SynergiZing ML and LLMs in R A tidymodels pipeline, a retrieval pipeline, a deployed API and a chat interface. RtidymodelsRAG

Nic Crane, PhDTeaches LLM-powered tooling in R See the course → Bundle Build Apps a Front Office Opens Daily The Complete Shiny Engineering Stack Modular architecture, custom components, mobile, and a real deployment. RShinyJavaScript

Veerle Eeftink-van LeemputTeaches production Shiny engineering See the course → Course Build Machine Learning Pipelines Python MachineZ scikit-learn end to end, with evaluation honest enough to survive review. Pythonscikit-learnGAMs

Patrick McFarlaneTeaches predictive modeling on sports data See the course →

Prices live on each course page, which is also where you enroll.

How it works

One session, and everything it leaves behind.

The order matters. Each stop exists because the one before it happened.

You turn up

A live room

Taught by someone who does this work, with moderated Q and A, so you ask the question you actually have rather than the one a recording anticipated.

Already set up

The environment

Pre-configured with the packages and system dependencies that session uses, at pinned versions. Nothing to install, no version drift.

It stays yours

You keep everything

Session code, notes and cheat sheets, and a recording with a 30-day replay window. What gets built in the room does not close with it.

Once a month

The Film Room

The Career session takes what the other tracks taught and works it into portfolio and interview material.

What gets built

The skills teams are actually hiring for.

Not a syllabus. These are the artifacts that come up in a technical conversation, in the languages the job descriptions actually name, and every one of them is taught live by someone who builds them.

Bayesian hierarchical modeling

Partial pooling, priors, and full posteriors in PyMC and in Stan, with the diagnostics that say when to stop trusting a fit. NumPyro where the model needs the speed.

Python and R · Modeling track

Deploy and monitor in production

Containerized, pinned, and shipped to cloud: Docker images, CI gates, lockfiles for both languages, and a service that keeps running after the person who built it moves on.

Docker, CI/CD, GCP and AWS · Production track

Computer vision from video

Detection and tracking models over game footage, the labeling workflow behind them, and the extraction pipeline that turns frames into spatiotemporal data you can actually model.

Python, PyTorch · Sports Analytics track

Real-time and streaming data

Live-streaming inputs scored as they arrive, with low-latency paths and the honest question of what a number means when it is still moving.

Python and R · Production track

LLM tools and evaluation

Retrieval pipelines with evaluation harnesses around them, so behavior is measured rather than asserted, and a result can be explained to someone non-technical without hand-waving.

Python and R · LLM Tools track

Production-grade analytics applications

Full-stack tools people actually open: modular architecture, custom components, R talking to JavaScript over the socket, mobile and offline.

R, JavaScript · App Development track

Agentic AI workflows

Planning work so it can be delegated, running delegated builds, automated browser QA, and validation gates. The loop we run our own work through, taught as a practice rather than a tool demo.

LLM Tools and Production

Every one of these is taught live by a working practitioner, in the language the work is actually done in.

The catalog

9 self-paced courses and 3 bundles.

The live rooms are where the method is taught. The courses are where you go when you need the whole thing end to end, on your own clock.

Start here

The two foundations everything else sits on, one in each working language. If you are not sure which, take the one in the language your target work is written in.

2 courses

Modeling and machine learning

Uncertainty done properly and pipelines that survive review. This is the stack quantitative and machine learning roles screen for hardest.

3 courses

Application development

Turning analysis into something people open. Modular architecture, custom components, mobile, and deployment.

3 courses

LLM tools and AI

Building with models rather than prompting them, with evaluation attached so behavior is measured rather than asserted.

1 course

See all courses What Membership includes

Coming up

The next few live rooms.

Live masterclasses every week, across six tracks. Every one is taught by somebody who does this work.

Next up The Film Room: The Portfolio That Gives the Tour Mon 31 Aug · 15:00-16:15 EDT / 21:00-22:15 CEST
Michael S. Czahor, PhD See this week’s sessions

The Film Room: The Portfolio That Gives the Tour, taught by Michael S. Czahor, PhD

Mon 31 Aug15:00-16:15 EDT / 21:00-22:15 CEST The Film Room: The Portfolio That Gives the Tour Michael S. Czahor, PhD Builds sports analytics products and runs hiring-side reviews. This session: portfolio sites that give the tour. Career

The Farm System: Modular App Design for Shiny, taught by Veerle van Leemput

Fri 4 Sep09:00-10:15 EDT / 15:00-16:15 CEST The Farm System: Modular App Design for Shiny Veerle van Leemput Builds production Shiny applications for sport. This session: modular app architecture. App Development

Ask the Box Score Anything: Natural Language Queries with querychat, taught by Nic Crane, PhD

Wed 9 Sep09:00-10:15 EDT / 15:00-16:15 CEST Ask the Box Score Anything: Natural Language Queries with querychat Nic Crane, PhD Builds LLM-powered data tools in R. This session: natural language queries over real sports data. LLM Tools

The No-Look Pass: Sharing State Between Shiny Modules, taught by Veerle van Leemput

Fri 11 Sep09:00-10:15 EDT / 15:00-16:15 CEST The No-Look Pass: Sharing State Between Shiny Modules Veerle van Leemput Builds production Shiny applications for sport. This session: module state and app structure. App Development

Paper to Pipeline: Turning Scouting Reports into a Production App with Claude, taught by Michael S. Czahor, PhD

Wed 16 Sep16:00-17:15 EDT / 22:00-23:15 CEST Paper to Pipeline: Turning Scouting Reports into a Production App with Claude Michael S. Czahor, PhD Builds sports analytics products and runs hiring-side reviews. This session: document AI for scouting workflows. Sports Analytics

Kickoff to Production in Minutes: Claude Code for Sports Analytics Shiny Apps, taught by Stefan Linner

Thu 17 Sep10:00-11:15 EDT / 16:00-17:15 CEST Kickoff to Production in Minutes: Claude Code for Sports Analytics Shiny Apps Stefan Linner Deploys data applications to production. This session: AI-assisted build and deployment of Shiny apps. Production

Join the Masterclass See the full schedule

Workshop · now booking

Build a no-code analysis board in R, in three hours.

Run with cynkra and taught by David Granjon. You write five blockr blocks, wire them into a board, and put your own data behind it. Built live on a stage of the Tour de France Femmes.

Live positions
Road profile
Radio Tour
Gaps and groups
Stage board

See the workshop September 24, then October 1 · three hours · live

Swipe the stage sideways

Breakaway Chase Peloton

Schematic. Ours, drawn for this page: the climbs are categorized but deliberately unnamed and the elevations are invented, because a drawing should not be mistaken for a reading. The distance, the eight categorized climbs, the ascent and the snapshot count above are the real ones.

What people who hire say

The people on the other side of the table.

Brad Smith, PhDSenior Performance Analyst, University of NebraskaSports Analytics Professor, Data Science Program, NorthwesternPlayer Development Analyst, New York Yankees 2018-2021

I've always been intrigued by the intersection of sports analytics and data science. AthlyticZ provides students with the perfect platform to explore this passion. The hands-on projects are particularly empowering, allowing them to apply theoretical concepts to real-world scenarios.

Bill Geivett, M.Ed.President, IMA TeamAuthor, Do You Want to Work in Baseball?Sr. VP, Colorado Rockies 2001-2014Asst. GM, Los Angeles Dodgers 1998-2000

AthlyticZ has completely transformed the learning approach to data science through the use of sports-based problems. The instructors are the best of the best, and the practical projects have immediate impact to students.

Trimmed with permission.

Adam UnesSenior Director, Analytics, Excel Sports Management

The sports industry moves fast. Managing the pace of evolving technology, data, and AI isn't optional - it's imperative. Our Analytics team was looking for a partner to meet us where we are, to help us in the continued investment of our people and capabilities without pulling us away from the work that matters. AthlyticZ delivers exactly that: a structured, practitioner-led platform that fits how modern sports analytics groups actually operate.

Bryce MurphyDirector of Performance Science and Innovation, IMG Academy

We've teamed up with AthlyticZ to supercharge how we use data science and statistics to impact our sports. More clarity in the numbers means bigger results for our athletes.

From a public LinkedIn post.