AT&T reduces fraud by up to 80% with the Databricks Data + AI Platform

Overview

AT&T migrated from a legacy on-premises, rules-based fraud detection system to the Databricks Data + AI Platform, moving to a unified lakehouse architecture. AT&T now runs over 100 ML models in production that use real-time data, automatic alerts and recommendations to protect its 182 million wireless customers from fraud including robocalls, robotexts, illegal unlocks and identity theft, reducing fraud by up to 80%.

The challenge

AT&T needed to protect its 182 million wireless customers from fraud — including robocalls, robotexts, gaming, illegal unlocks and identity theft — amid 10 million transactions occurring every second, but its legacy on-premises, rules-based architecture created infrastructure complexity and failed to deliver the innovation needed for an optimal customer experience.

The solution

AT&T modernized its data infrastructure in the cloud with the Databricks Data + AI Platform, moving to a unified lakehouse architecture on Delta Lake. AT&T now runs over 100 ML models in production that use real-time data, automatic alerts and recommendations to protect customers and arm employees across AT&T's operations, replacing the prior rules-based fraud system.

Reported business value

AT&T has reduced fraud by up to 80% with over 100 fraud detection ML models in production, saving millions of dollars in potential fraud costs.