Streak Tool

Probability of winning or losing streaks from your win rate and streak length.

Please enter a probability between 0.1% and 99.9%
Results
P(Winning Streak of Length N) --
P(Losing Streak of Length N) --
Expected Longest Run --
P(≥ 1 such streak in N bets) --

How to Use This Calculator

  1. Type in your single-bet win probability as a percentage (e.g., 55)
  2. Type in the streak length you want to test
  3. Type in the total number of bets
  4. Read off the streak probability and expected longest run

Formula

P(streak of N wins) = p ^ N

P(streak of N losses) = (1 − p) ^ N

Expected Longest Run (approx) = log(N · (1 − p)) / log(1 / p)

P(≥ 1 winning streak of length N in M bets) ≈ 1 − (1 − p^N)^(M − N + 1)

Frequently Asked Questions

Why is my expected longest streak so long?

Variance scales logarithmically with sample size. Over 1000 coin flips you’ll usually hit a run of 9-10 heads. Long streaks feel shocking but are mathematically expected — most bettors misread them as hot/cold spells instead of plain variance.

How does streak length affect bankroll management?

Even a 60% win rate throws off 5+ losing streaks routinely. Your bankroll plan (Kelly fractions, flat staking) has to ride these out without busting. Run a streak length of 5-7 here to gauge how often such losing runs hit, then size your unit to match.

Do sports streaks predict anything?

Mostly no. Independent events (coin-flip-style markets) generate streaks by pure chance. Small predictive effects exist (injury cascades, team morale) but tend to be overhyped. Treat past streaks as variance unless a concrete model gives you reason not to.

What's the math behind 'expected longest run'?

For independent Bernoulli trials with success probability p over N trials, the expected longest run of successes converges to log(N(1−p))/log(1/p). It’s a logarithmic approximation, accurate for large N, that yields the typical longest streak you’d see.