Skip to main content

Fraud Metrics

Prerequisites

Before diving into fraud metrics, understand:

TL;DR
  • Loss metrics: Fraud rate 5-50 bps typical; Net fraud loss = Gross - Recoveries
  • Detection targets: Detection rate over 90%, false positive rate under 50%, precision over 50%
  • Operational: Review rate 1-5%, manual review under 5 min, auto-decision over 95%
  • Prevention balance: Block rate + friction rate vs. insult rate
  • Segment by: fraud type, channel, product, customer segment, geography

Key performance indicators for measuring fraud program effectiveness.

Loss Metrics​

MetricDefinitionBenchmark
Fraud Rate (bps)Fraud $ / Transaction $ × 10,0005-50 bps
Fraud Rate (#)Fraud count / Transaction count0.05-0.5%
Gross Fraud LossTotal confirmed fraudBefore recoveries
Net Fraud LossGross - RecoveriesTrue P&L impact

Detection Metrics​

MetricDefinitionTarget
Detection RateDetected fraud / Total fraud>90%
False Positive RateGood transactions blocked / Total blockedUnder 50%
PrecisionTrue fraud / All flaggedOver 50%
RecallDetected fraud / All fraud>90%

Operational Metrics​

MetricDefinitionTarget
Review RateTransactions reviewed / Total1-5%
Manual Review TimeAvg time per caseUnder 5 minutes
Auto-Decision RateAuto-approved or declined / TotalOver 95%
Time to DetectionTransaction to fraud confirmationUnder 7 days

Prevention Metrics​

MetricDefinitionNotes
Block RateTransactions blocked / Total attemptsHigher isn't always better
Friction RateStep-ups triggered / TotalBalance UX vs. security
3DS Challenge RateChallenges / Total 3DS5-15% typical
Insult RateGood customers declinedMinimize

Segmentation​

Track metrics by:

Next Steps​

Setting up fraud tracking?

  1. Understand fraud types - Know what you're measuring
  2. Define risk appetite - Set acceptable thresholds
  3. Review industry benchmarks - Know what "good" looks like

Fraud rate too high?

  1. Implement risk scoring - Better detection
  2. Add velocity rules - Catch patterns
  3. Consider 3DS - Liability shift for fraud

Optimizing detection?

  1. Review rules vs ML - Choose right approach
  2. Tune manual review - Reduce false positives
  3. Evaluate vendors - Consider specialized tools