Bankroll tool

Kelly Criterion Calculator

Find the mathematically optimal stake for any bet. Enter the odds, your honest estimate of the win probability, and your bankroll — we compute full, half, and quarter Kelly along with the expected value of the wager.

Kelly Bankroll Calculator

Find the mathematically optimal stake for your edge.

Kelly multiplier

Recommended stake

$27.50

To win

$25.00

Your edge

2.6pts

Full-Kelly would risk 5.5% of your bankroll. Most disciplined bettors use Half or Quarter Kelly to smooth variance — this stake reflects your selected multiplier.

The Kelly criterion maximizes long-run bankroll growth, but only if your win-probability estimate is accurate. Garbage in, garbage out — overestimating your edge leads to over-betting. This tool is for education, not financial advice.

How the Kelly Criterion works

Kelly sizes each bet as a fraction of your bankroll based on your edge and the payout. For a bet at decimal odds d (so net fractional odds b = d − 1) with a true win probability p and loss probability q = 1 − p, the optimal fraction is:

f* = (b·p − q) / b

Worked example

Say you have a $1,000 bankroll and bet a game at −110 (decimal 1.909, so b = 0.909) where you estimate a 55% win probability.

  1. 1. Edge over the market: −110 implies 52.4%, so your 55% estimate is a 2.6-point edge.
  2. 2. Full Kelly: (0.909 × 0.55 − 0.45) / 0.909 ≈ 5.5% → $55.
  3. 3. Half Kelly (recommended): half of that, $27.50 — the same edge with far smoother variance.

Plug those exact numbers into the calculator above and you'll see these figures returned. The honesty of your win-probability estimate is everything: garbage in, garbage out. Pair this with our verified pick track record to sanity-check the probabilities you're working with.

Frequently asked questions

What is the Kelly Criterion?
The Kelly Criterion is a formula that determines the bet size that maximizes the long-term growth rate of your bankroll. It stakes more when you have a bigger edge and less when the edge is thin, and it never risks your entire bankroll on one bet.
Why would I use half or quarter Kelly?
Full Kelly is highly aggressive and assumes your win-probability estimate is exactly right. Because real estimates carry error, most disciplined bettors use half or quarter Kelly to smooth out variance and reduce the risk of large drawdowns while keeping most of the growth benefit.
What happens if my edge is negative?
If your estimated win probability is lower than the probability implied by the odds, Kelly returns a stake of zero — the bet has no positive expected value, so the mathematically correct wager is nothing.