Bot detection on Betfair Poker
Bot detection on Betfair Poker is implemented as a weighted composite of behavioural signals which triggers enforcement when the aggregate score crosses a threshold. The system operates at two tiers: network-wide statistical scrutiny administered by Playtech across all iPoker skins, and operator-level KYC and account review administered by Betfair.
The two-tier model
Betfair Poker does not run its own poker engine. It is a skin on the iPoker Network, so anti-cheat operates at two levels that a bot has to clear simultaneously.
- Network tier (Playtech). The shared layer watches behaviour across every iPoker skin at once. The same hand histories, timing data, and account graph feed one detection pipeline. A pattern that looks fine on Betfair alone can stand out against the whole network.
- Operator tier (Betfair / Flutter). Betfair handles its own KYC, payments monitoring, and responsible-gambling checks. This tier is slower and more manual. It handles identity verification and withdrawal review, with authority to freeze funds pending investigation.
The two tiers catch different things. The network tier is automated and behavioural, flagging how you play. The operator tier is forensic and financial, flagging who you are and how the money moves. Passing one tier's checks says nothing about passing the other's. An account must satisfy both.
Reading the signal book
The chart above and the table below rank the signals a modern behavioural model weighs. The weights are illustrative, but the ordering reflects what is genuinely hard to fake versus what is cosmetic. Timing and coordination sit at the top; strategy does not. Detection rarely tries to prove "this play was too good." It looks for machine-like timing and coordination.
| Signal | Weight | What it captures | Hard to fake? |
|---|---|---|---|
| Action-timing variance | 0.95 | Whether decision times vary like a human's (slower in tough spots, faster in trivial ones) | Very hard |
| Multi-table action sync | 0.84 | Correlated timing or sizing across several seats run by one operator | Very hard |
| Bet-sizing entropy | 0.70 | Whether sizes cluster on solver outputs instead of the messy spread humans use | Hard |
| Mouse / input cadence | 0.53 | Movement paths, click jitter, and idle micro-motion between actions | Medium |
| Win-rate vs. variance fit | 0.43 | A win rate too smooth for the volume, with too little downswing for the sample | Medium |
| Tabling-hours pattern | 0.28 | Sessions that start and stop on machine-like schedules, around the clock | Easy |
| Session-length regularity | 0.17 | Identical session durations with no human drift or fatigue | Easy |
The weighting explains why "make the bot play slightly worse" does little. Strategic quality is not among the highest-weighted signals. The dominant signals are timing variance and cross-table coordination, which a crude script handles badly and a multi-account fleet cannot avoid. That is also where bots differ most from each other: a serious one ties its hesitation to how hard the spot is, and a player who runs it on one account at a normal table count gives the second-heaviest signal no fleet pattern to read. Dumping a few pots to soften a win rate is no substitute for either.
Why timing dominates
Human decision time correlates with difficulty. People snap-fold trash, tank on close river decisions and misclick occasionally. A naive bot acts in a tight, near-constant window regardless of the spot, and one that only adds randomised delays still produces a symmetric, stationary distribution unrelated to board texture. Detection models the joint distribution of decision time and decision difficulty, so plain noise does not help there. Timing therefore carries the heaviest weight and should be checked first when testing a bot. Decision time should follow the spot, not a random number.
Failure modes that get bots caught
In practice, bots are not usually caught by one elegant test. They are caught by a stack of ordinary mistakes that each nudge the composite score until it crosses the threshold. Each mistake is an avoidable habit, so detection risk can be managed.
- The fleet tell. Running many accounts to harvest liquidity creates synchronised timing, shared sizing tendencies, and a payments/device graph that ties them together. This is the second-heaviest signal.
- Sizing fingerprint. Snapping to a small set of solver-derived bet sizes produces low entropy that human play never shows; a histogram of a bot's sizes looks discrete where a human's is smeared.
- Too-smooth results. A graph with a clean upward slope and implausibly shallow downswings over a large sample is itself evidence. A lack of variance is suspicious.
- The KYC wall. Even an account with clean behaviour has to withdraw. On Betfair that means identity checks, source-of-funds questions, and payment patterns that the operator tier reviews independently of how the cards were played.
- The peek myth. Hole-card readers and RNG predictors are not a failure mode because they do not work. Card data is server-authoritative and encrypted, and the shuffle is a certified CSPRNG. Buying one loses money without cheating.
detection is a weighted, multi-signal system designed so that no single trick defeats it, so nothing here is about tricks. Keeping an account in good standing requires consistent practices over months: human-like timing and sizing, one account at a normal table count, a realistic device environment, volume that rises gradually and tidy finances for the KYC tier. Read it next to the bot economics page: the edge pays over volume in the right stake window, and this page is the risk you manage while that volume builds.
Weighing the detection risk against the cost? Ask the desk on Telegram for current pricing and a free trial of the bot.
Check Bot Price