Case Study: Large US-Based Bank achieves real-time insider threat detection, 5x scope expansion and 10x cost reduction with Gathr

Real-time insider threat detection solution for a Fortune 500 bank

Large US Based Bank, a large U.S.-based financial services corporation known for its extensive credit card business, faced growing insider-threat risks that static, rule-based detection could not reliably catch. Their legacy relational stack was expensive, inflexible, and limited threat visibility to only 15–20% of sensitive applications, produced large numbers of false positives, and required months to years to move use cases into production. To address this, the bank engaged Gathr to apply a cloud-native, streaming data-pipeline platform with built-in machine learning and real-time analytics for insider threat detection.

Gathr ingested and processed data from 80–90% of critical customer-facing and operational applications, handling 85M records/day at 98,000 events/second and delivering a 5x expansion in scope with a 10x reduction in infrastructure cost and a 4x performance boost. Using Gathr’s ML-driven anomaly detection, in-memory transformations, and real-time alerts, false positives dropped from hundreds/thousands per day to tens, and the threat detection application was redeveloped in three weeks and moved to production in eight weeks (roughly 10x faster than the prior solution), enabling timely, accurate prevention of predicted breaches.