AI Case Study
Western Union reduces fraud rate to below 1.2% using machine learning models for detection
Western Union, in partnership with Cloudera, has reduced its digital transaction fraud rate to well below the industry standard of 1.2%. It has employed a variety of different machine learning systems to do so, although this has resulted in an increase in false positives.
Western Union has now turned to machine learning models to detect fraud, in partnership with Cloudera Data Science Workbench. The company says it uses "more than 100 active machine learning models" which "pull all the data from the Hadoop cluster and find the patterns, find the anomalies, and then we …. validate the model and put the model into our production system.”
Money transfer order requests go through the Hadoop cluster and a decision is returned as to whether or not it is legitimate.
Western Union does not disclose fraud rate but says "it’s significantly below the industry standard of 120 basis points, or 1.2%" and is "much, much lower than before”. However, the company notes that the downside to these methods is an increase in false positives.
Reportedly Western Union uses a "collection of machine learning models – including logistic regressions, random forests, and some boosting algorithms — [which] analyze a complex host of variables and make many calculations, including how reliable a potential user is and how much risk they pose to the company".
"Depending on the specific sector of the financial services industry, fraud losses can account for upwards of 5% of the value of transactions. In the sector that Western Union works in, the benchmark figure is about 1.2%. Like other firms, Western Union employs a multi-pronged attack to thwart fraud. When money is sent in person, there are ways to check the identities of the money transfer participants, which helps to keep fraud down. But some of those authentication techniques can’t be used for validating transactions that occur digitally".
"Hundreds of variables" are analysed including customer behaviour, transaction location origination, recipient, etc.