I’ll try to sketch a tiny notebook and share — could help others get started quicker.

If you post a sample notebook, I’d totally fork it and try modifying the priors. Love hands-on examples.

Also include examples with small sample smoothing (empirical Bayes) — saves you from overfitting on few games.

Noted — adding a code appendix is on the roadmap. We’ll include a couple of simple Python snippets (pandas + numpy + simple Monte Carlo) next update.

That’s sensible. The guide’s conservative plan is built for small bankrolls — prioritize higher-confidence, lower-variance edges until you scale.

How do you measure that >10% edge? Manually or via a model?

Model + line shopping. If model says 60% and book implies 50%, that’s 10% edge. But also consider vig and potential for move.

Also add ‘correlation surprise’ when two correlated events happen unexpectedly (e.g., QB injured leading to backup RB usage).