Anomalous Account Behavior Detection

Spotify's Trust & Safety team has flagged a spike in anomalous account behavior — accounts with listening patterns consistent with credential sharing, bot-driven stream farming, or compromised accounts. These accounts inflate streaming metrics, distort royalty payouts, and degrade recommendation quality. You need to design signals for detecting different types of anomalous behavior, set appropriate thresholds, reason about false positive tolerance, and define success metrics for a fraud detection system.

Skills tested

Interview stages

• 1Design signals for different anomaly types
• 2Set thresholds and reason about false positive tolerance
• 3Measure fraud detection success

What you'll get back

After the session, you'll receive a detailed AI-generated debrief with stage-by-stage ratings (Strong / Developing / Weak), a signal coverage map showing which key points you hit, specific feedback on your reasoning and communication, and a reference response for comparison.