Build a sports betting bot
that actually makes money

6 Jupyter notebooks take you from zero to a live trading bot. Beginner-friendly — works with AI assistants like Claude or ChatGPT.

Works with Polymarket, Kalshi, DraftKings, FanDuel, Pinnacle, and any sportsbook or prediction market.

Get the Course — $49 Free First Lesson

One-time purchase. Instant download. No subscription. No coding experience required.

215
Notebook cells
6,080
Lines of working code
6
End-to-end modules
73.0%
Backtest win rate

Works with AI assistants

New to Python? Every notebook is designed to work with Claude, ChatGPT, or any AI coding assistant. Paste any cell into an AI, ask "explain this" or "help me customize this for soccer," and get step-by-step guidance. You don't need to be a programmer to build a working bot.

Paste & ask
"Explain this code"
Customize
"Add soccer support"
Debug
"Why is this error?"

Real backtest results from this system

Sport Trades Win Rate Avg Profit/Trade
NBA 212 66.5% +10.9c
NCAAMB 599 75.3% +10.4c
NHL 83 68.7% +7.0c
CFB 1,349 73.1% +9.4c
NFL 367 76.3% +5.4c
All 2,610 73.0% +9.9c

Time-split validation. Tested against real market prices. Held to settlement, net of fees.

What you'll build — module by module

1

Scraping ESPN

  • Build an async data scraper for ESPN play-by-play
  • Handle rate limits, retries, and API pagination
  • Fetch 60,000+ games across 7 sports
  • Store as efficient Parquet files

Production-grade data pipeline in 1 notebook

Try free ↓ · AI prompt: "Explain how this async scraper works"

2

Elo Ratings

  • Implement Elo from scratch (no libraries)
  • Home advantage, K-factor tuning, season resets
  • 907+ NCAAMB teams, 258+ per sport
  • Validate against known rankings

The simplest feature that matters most

AI prompt: "Help me add season-decay to my Elo system"

3

WP Models

  • Train LR+Spline and XGBoost+Isotonic
  • Isotonic calibration for probability accuracy
  • Why simpler models beat complex ones for trading
  • Sport-specific feature engineering

Worse Brier score = more trading profit

AI prompt: "Explain isotonic calibration like I'm a beginner"

4

Backtesting

  • Time-split validation (train on N-1, test on N)
  • Adverse selection and underdog traps
  • Execution cost modeling (fees, slippage)
  • Deduplication and subsampling

Every mistake that blows up your backtest

AI prompt: "Help me add a new sport to this backtest"

5

Live Bot

  • Polymarket CLOB API integration
  • ESPN adaptive polling (5s/15s)
  • Edge detection and signal generation
  • Order execution with shadow mode

A working bot you can run tonight

AI prompt: "Help me add Discord alerts to this bot"

6

Deployment

  • FastAPI server with HTTPS
  • Discord alert webhooks
  • Cron scheduling and monitoring
  • Cloudflare Tunnel for secure access

From laptop to 24/7 production

AI prompt: "Help me deploy this to a $7/mo VPS"

Try Module 1 free

Scraping ESPN: build an async data pipeline that fetches 60,000+ games. Enter your email to download the full notebook instantly.

Download Module 1 Notebook

Check your email for the download link too.

No spam. Unsubscribe anytime.

Frequently asked questions

What do I need to get started? +
Python 3.10+, pandas, numpy, scikit-learn, xgboost, aiohttp, matplotlib. A Polymarket account is only needed for Module 5 (live trading). Everything else works locally.
What skill level is this for? +
Complete beginners welcome. No prior Python or ML experience needed. Every notebook includes step-by-step explanations and is designed to work with AI coding assistants (Claude, ChatGPT, Copilot). If you get stuck on any cell, paste it into an AI and ask "explain this line by line" or "help me fix this error" — you'll get an instant walkthrough.

What you DO need: A computer (Mac, Windows, or Linux), an internet connection, and the willingness to follow instructions and experiment. The notebooks handle the rest.
Is there a refund policy? +
30-day conditional guarantee. Complete all 6 modules, follow the instructions, and if you can't get a working bot with a positive backtest within 30 days, email admin@zenhodl.net with your notebook outputs and we'll issue a full refund.

We're confident because the system works — 71.9% backtest win rate across 1,552 trades. Plus you can try Module 1 completely free before buying to make sure you like the teaching style.

Note: Refund requires demonstrated completion of all modules. Dataset purchases are non-refundable.
How do I use AI with this course? +
Every notebook cell is self-contained and well-commented. If you don't understand something:
  1. Copy the cell into Claude, ChatGPT, or any AI assistant
  2. Ask: "Explain this code line by line" or "What does this function do?"
  3. To customize: "Help me modify this to track soccer instead of NBA"
  4. To debug: paste the error message and ask "How do I fix this?"

Think of it as having a patient tutor sitting next to you. The notebooks give you the working code — the AI helps you understand and extend it.

How long does it take to complete? +
Most people finish in 1-2 weekends. With an AI assistant, you can move even faster — it'll explain any concept or debug any error in seconds. Each module is a self-contained notebook designed to run end-to-end.
Will this work for my sport? +
The course covers NBA, NFL, NCAAMB, CFB, NHL, Soccer, CS2, LoL, Tennis. The techniques generalize to any sport with prediction markets.
What's the difference between the course and the API? +
The course teaches you to build your own system. The API ($149/mo) gives you our pre-built signals in real-time — for traders who want results without building. Many customers start with the course and upgrade to the API later.

Start building your own edge

6 notebooks. Working code. Real backtest results. $49 one-time.

Get the Course — $49

or browse training datasets →