Databricks > Case Studies > AT&T's Transformation: From Legacy Infrastructure to Cloud-Based Lakehouse for Enhanced Fraud Detection

AT&T's Transformation: From Legacy Infrastructure to Cloud-Based Lakehouse for Enhanced Fraud Detection

Databricks Logo
Technology Category
  • Analytics & Modeling - Machine Learning
  • Cybersecurity & Privacy - Intrusion Detection
Applicable Industries
  • Construction & Infrastructure
  • Retail
Use Cases
  • Fraud Detection
  • Real-Time Location System (RTLS)
Services
  • Data Science Services
  • Training
About The Customer
AT&T is a leading communication service provider dedicated to providing its 182 million wireless customers with secure, reliable, and frictionless communications. The company handles 10 million transactions every second and is committed to staying ahead of fraudsters. AT&T's commitment to harnessing the power of data and AI to stop attacks before they happen is evident in their decision to modernize their data infrastructure. The company's goal is to provide an optimal customer experience by reducing fraud and delivering more data-driven solutions that will help to democratize AI across the business.
The Challenge
AT&T, a leading communication service provider, was facing challenges with its legacy on-premises architecture. Despite having 182 million wireless customers and handling 10 million transactions per second, the company was struggling to stay ahead of fraudsters. The existing infrastructure was complex and failed to deliver the innovation required for an optimal customer experience. The company was using rule-based technology for fraud detection, which was reactive rather than proactive, making it difficult to stay ahead of sophisticated fraud attempts. The process was not only protracted, inefficient, and resource-heavy, but also expensive. AT&T also struggled to gain real-time insights and automation necessary to optimize dispatch. The company could not unify data points to match a technician’s troubleshooting skills to the customer issue and location, leading to increased operational costs and a negative impact on customer experience.
The Solution
AT&T decided to modernize their data infrastructure by moving from an on-premises architecture to a cloud-based lakehouse with Databricks. This allowed AT&T to take in all kinds of data, standardize it, and then run Machine Learning (ML) models that drive fraud alerts in real time. The company first launched Databricks with their data science team, pumped their on-premises data into Delta Lake, moved their workloads to the cloud, and created a Center of Excellence (CoE) with training and community support to expand adoption and data democratization. Focusing on fraud detection as their first use case, the data science team was able to develop predictive solutions with unified data and AI, and seamless collaboration that stops fraud before it happens. AT&T plans to completely move off their on-prem data lake by 2023.
Operational Impact
  • The migration to Databricks Lakehouse has significantly improved AT&T's operational efficiency. The company has been able to proactively stop fraud before it happens, reducing fraud by up to 80% with over 100 fraud detection ML models in production. The new system has also enabled real-time, automatic fraud detection, replacing the previous rules-based system. This has not only saved millions of dollars in potential fraud costs but also improved the customer experience. The company now has a robust roadmap to deliver more data-driven solutions that will help to democratize AI across the business. AT&T is also planning to increase adoption for use cases benefiting dispatch, service reliability, quality of coverage, and sales growth.
Quantitative Benefit
  • 80% decrease in fraud attacks
  • Millions of dollars saved in potential fraud costs
  • Over 100 ML models in production for fraud detection

Case Study missing?

Start adding your own!

Register with your work email and create a new case study profile for your business.

Add New Record

Related Case Studies.

Contact us

Let's talk!
* Required
* Required
* Required
* Invalid email address
By submitting this form, you agree that IoT ONE may contact you with insights and marketing messaging.
No thanks, I don't want to receive any marketing emails from IoT ONE.
Submit

Thank you for your message!
We will contact you soon.