AI Case Study
American Express identifies $2 billion in potential annual incremental fraud incidents with machine learning
American Express has over 100 million credit card customers globally representing over $1 trillion in annual charge volume. Amex used machine learning models based on an understanding of customer spending patterns alongside normal merchant purchase information. This allowed real-time detection of potential fraud resulting in an estimate $2b in potential annual incremental fraud incidents.
Industry
Financial Services
Banking
Project Overview
"To detect fraudulent transactions quickly so as to minimize loss, the company employed a machine learning model that uses various inputs like card membership information, spending details, and merchant information which are pattern-matched against evolving algorithms in real time to flag transactions that have a high probability of being fraudulent."
Reported Results
Amex claims they identified $2b in potential annual incremental fraud incidents before the money was lost.
Technology
"The company employed a machine learning model that uses various inputs like card membership information, spending details, and merchant information which are pattern-matched against evolving algorithms in real time to flag transactions that have a high probability of being fraudulent. "
Function
Risk
Audit
Background
"With a database of over a 100 million credit cards globally, that account for over $1 trillion in charge volume every year, American Express deals with vast quantities of data." They were looking to better identify fraudulent transactions and built big data and machine learning capabilities.
Benefits
Data
"...card membership information, spending details, and merchant information"