by Angela Guess
Bernard Marr writes in Data Informed, “American Express handles more than 25 percent of credit card activity in the United States and, in 2014, surpassed handling $1 trillion in transactions. The company interacts with people on both sides of transactions: millions of businesses and millions of buyers. So it’s no surprise then that American Express has no shortage of data. The only question for the company is how to leverage all of that data. In 2010, the company realized that traditional databases no longer would be sufficient for the data and analysis that it wanted to handle, and so the company brought itself into the age of big data by upgrading to a Hadoop infrastructure and bringing in machine learning algorithms.”
Marr continues, “There’s an old saying that if you can consistently improve by just 1 percent every week, by the end of a year, you will have improved by 50 percent. That’s akin to the model that American Express has developed. Within the company, millions of decisions are made every day. If, by employing big data analytics and machine learning, the company can make even slightly better decisions, it would have a huge impact. One place in which the company has implemented machine learning algorithms is in the fraud detection and prevention department.”
He goes on, “The company is attempting to detect fraudulent transactions as quickly as possible to minimize loss, so it employed a machine learning model that uses of a variety of data sources including card membership information, spending details, and merchant information to detect suspicious events and make a decision in milliseconds by comparing that event to a large dataset. This has enabled American Express to detect more fraudulent transactions and save millions of dollars.”
photo credit: American Express