What factors are contributing to the sudden 50% increase in false positive alerts from Chainalysis's KYT (Know Your Transaction) service this quarter?

Introduction

The sudden 50% increase in false positive alerts from Chainalysis's KYT (Know Your Transaction) service this quarter is a critical issue that demands immediate attention. This surge in false positives could significantly impact our clients' operational efficiency and trust in our service. I'll approach this problem systematically, focusing on identifying the root cause, validating hypotheses, and developing both short-term fixes and long-term solutions.

Step 1

Clarifying Questions (3 minutes)

• Given the sudden increase, I'm wondering about recent system changes. Have there been any updates to the KYT algorithms or data sources in the past quarter?

Why it matters: Recent changes could directly correlate with the increase in false positives. Expected answer: Yes, there was a recent update to improve detection accuracy. Impact on approach: If confirmed, we'd focus on the update's impact and potential rollback.

• Considering the scale of the increase, I'm curious about the alert volume. What's the typical daily alert volume, and has this changed alongside the false positive rate?

Why it matters: Understanding the baseline helps quantify the impact and identify patterns. Expected answer: Around 10,000 alerts per day, with a 20% increase in volume. Impact on approach: A volume increase might indicate broader issues beyond just false positives.

• Thinking about user segments, are the false positives concentrated in specific transaction types or customer categories?

Why it matters: Segmentation could reveal targeted issues rather than system-wide problems. Expected answer: Higher concentration in cross-border transactions for institutional clients. Impact on approach: We'd focus on specific transaction flows or client segments for targeted solutions.

• Reflecting on external factors, have there been any significant regulatory changes or global events that might influence transaction patterns?

Why it matters: External events could explain changes in transaction behavior triggering more alerts. Expected answer: New AML regulations were introduced in a major market last month. Impact on approach: We'd need to assess our system's alignment with new regulatory requirements.

• Considering data integrity, has there been any change in how we're measuring or defining false positives?

Why it matters: Ensures we're comparing apples to apples and not facing a measurement issue. Expected answer: No changes in measurement methodology. Impact on approach: If confirmed, we can rule out measurement errors and focus on actual performance issues.