ProbBrain
🧮 Tool
Live
← back to dashboard

Polymarket Kelly Calculator

Robust Kelly with Bayesian credible-bound shrinkage, walk-the-book pricing, and Monte Carlo bankroll simulation. The cascade below shows you exactly why the recommended size isn't bigger.

Position
$10,000
3 levels past top
Belief
27%
→ Beta(α=9.10, β=22.90)
75%
Sizing
0.25
Recommended size
$—
enter inputs to compute
Decomposition cascade
Each minus-row is the dollars the previous step shrinks by. Hover any row for the reason.
Naive Kelly
Robust Kelly
Book-aware
Final f
Monte Carlo bankroll · 10k trajectories
P(reach 2×)
P(below 0.5×)
Median final
Max drawdown · p50
DD · p5 / p95
Final · 25–75%
Final · 5–95%
Edge (conservative, post-shrink)
Edge (raw, point estimate)
Spread cost
m_eff (after walking book)
Decimal odds offered (b)
$ return per $ staked (raw)
Log-growth · g per bet
Log-growth · annualized
KL divergence vs market
P(win) used
How the math works

Naive Kelly: f = (p_win − m) / (1 − m) where m is the displayed price and p_win your point estimate.

Robust shrink: we don't trust your point estimate. We treat your belief as Beta(p̂·n + 1, (1−p̂)·n + 1) with n from the confidence radio, then take the (1−CL)/2 tail as p_conservative. Kelly is recomputed at this lower bound. Robust-optimization choice over the credible set, not posterior-mean shrinkage (Bayesian Kelly with log utility doesn't shrink).

Walk the book: your stake doesn't fill at top of book. We solve for the fixed point S* = bankroll · (p_cons − m_eff(S*)) / (1 − m_eff(S*)) with a damped iteration. m_eff is the volume-weighted fill price walking through the input depth.

Fractional Kelly: finally multiplied by your chosen fraction (¼ Kelly common — halves variance, only modestly reduces growth).

KL divergence: p·log₂(p/m) + (1−p)·log₂((1−p)/(1−m)). The asymptotic Kelly growth rate of full-Kelly betting at fair odds. "Bits of disagreement with the market."