Case Study

Fewer false positives, better signal clarity

For this travel booking platform, fraud was hiding in complexity. International bookings, third-party processors, and large-ticket transactions all made detection harder. While their model could flag some risk, it lacked the signal resolution needed to separate false positives from real threats.

The challenge

This platform processes hundreds of thousands of flight bookings per month, including many that pass through third-party processors. High-value, high-risk bookings, like international or premium-class tickets, carried a higher risk. However, the system in place was not calibrated to identify who could actually be trusted.

False positives drained revenue. Missed fraud created chargebacks and policy abuse. Analysts lacked the signal precision needed to tune the system without tradeoffs. The company needed a way to improve model performance at both ends of the spectrum. Their priority was high-impact bookings where decisioning was most opaque.

Their goals were clear

The hard part wasn't naming them, it was hitting all four at once without one undermining the others:

Improve fraud detection across complex booking types

Reduce false positives that were blocking legitimate travelers

Strengthen identity signals for users masked by third-party noise

Build analyst confidence in trust scores for better rule precision

Where static systems broke down

A static fraud model can read clean signals, but it can't make sense of noise. By the time the team brought in Pipl, three problems were stacking up across the platform.

Third parties disrupted signal lineage

External processors stripped or replaced core user signals, making it harder to link booking data to an identity and limiting the accuracy of risk scoring.

Late detection made fraud irreversible

Fraud was often flagged after booking confirmation, but by then the platform had already issued tickets, absorbed the cost, and lost the ability to intervene.

Missing signals were the signal

Attributes like email, phone, and address weren’t just weak, they were incomplete or unverifiable. The system didn’t interpret that absence as meaningful risk, leaving fraud undetected.

How the system changed with Pipl

Pipl calibrated Trust Scores using 165,000 historical flight bookings. Instead of relying on perfect input data, the model was trained to recognize meaningful patterns in partial, obscured, or fragmented signals. It performed especially well on traffic routed through third-party processors, where identity clarity was lowest. The team tested a range of scoring thresholds to capture both high-risk and high-trust segments with precision.

Incomplete or unverifiable attributes like phone carriers or address validation were treated as signals, not gaps

Thresholds like 250 and 850 were optimized to catch fraud earlier and approve good users faster

Scoring logic adapted to third-party data noise, enabling confidence even when visibility was limited

Model performance held strong across complexity, reaching a ROC-AUC of 0.87 even with limited ground truth

Pipl's proof of signal intelligence

220%

more risk on unvalidated addresses

72%

more fraud on never-seen emails

55%

more trust from low-risk ISPs

25%

more trust on previously seen phones

The real win? Trust decisions without clean data

The breakthrough wasn’t just in performance, it was in flexibility. Pipl gave the team a model that could make smart, confident decisions even when key attributes were missing or inconsistent.

Instead of defaulting to caution, analysts could act on trust scores that accounted for processor-level noise, international bookings, and limited visibility. This meant fraud was caught earlier, approvals moved faster, and the system adapted to complexity without overreacting to it.

Get these results for your organization

ROC-AUC reached 0.87

Trust scoring cleanly separated good and bad users, even in third-party-obscured transactions

Fraud detection reached 37% at a 250 threshold

Low-threshold tuning enabled stronger risk capture without excessive false positives.

Good detection reached 53% at an 850 threshold

Trust signals surfaced credible bookings faster, improving overall approval velocity.

False negative rate dropped to 1.6% at a 950 threshold

The highest confidence zone excluded almost all remaining fraud, enabling near-automatic approval.