Readable sub-scores
See device, network, multi-account, location, bot, identity, takeover and transaction risk separately.
Decision engine
Turn evidence intoa decision you can defend.
Combine transparent sub-scores, tenant rules, lists, velocity, graph context and an optional interpretable model into allow, monitor, review, challenge or block outcomes.
Live evidence
Challenge
Current analysis
Risk decision
Device84%
Network62%
Rules91%
RiskDeviceNetworkRulesEvidence
Evidence attached
8
explainable risk dimensions
JSON
versioned rule conditions
100%
decision history retained
Built for the full investigation
Useful to engineering. Clear to fraud operations.
The same evidence powers API decisions and investigator views, so policy changes stay connected to the behavior behind them.
No-code rule primitives
Compose typed WHEN/THEN conditions across scores, events, velocity, lists and account properties.
Safe backtesting
Replay historical sessions with rules on and off without rewriting stored decisions or risk history.
Interpretable ML
Train a tenant-specific logistic model from investigator labels and inspect its metrics and weights.
The operating flow
Move from signal to action without losing the explanation.
Assemble current context
Trueonic gathers the session, account, graph, velocity, lists, labels and network evidence.
Score and apply policy
Transparent sub-scores feed the overall risk score before tenant rules add signals or escalate the result.
Return the full explanation
Your service gets the outcome, scores, signals, reasons, rules version and request ID in one response.
Start with one protected workflow
Ship policy changes without creating a black box.
Start with sensible thresholds, add rules for your business, then learn from confirmed fraud and legitimate labels.