Amazon Web Services (AWS) released Amazon Fraud Detector for use by the general public, the company announced in a press release. Merchant fraud journal covered the creation of Fraud Detector when it was announced at the end of last year.
Amazon aggressively disrupts industries and accounts for nearly 50% of all eCommerce based transactions in the US. It will have plenty of data to create sophisticated models. At the time, we argued that while eCommerce fraud prevention solutions servicing the enterprise market have little to worry about, those serving the SMB market may suddenly find themselves with a strong new competitor.
“Amazon Fraud Detector provides a fully managed service that uses machine learning for detecting potential fraud in real time (e.g. online payment and identity fraud, the creation of fake accounts, loyalty account and promotion code abuse, etc.), based on the same technology used by Amazon.com—with no machine learning experience required,” Amazon said in a press release. “With Amazon Fraud Detector, customers use their historical data of both fraudulent and legitimate transactions to build, train, and deploy machine learning models that provide real-time, low-latency fraud risk predictions.”
Little wonder the general release is occurring just in time for the start of holiday shopping (and fraud) season. COVID-19 makes the full picture unknowable, but the expectation remains that online sales will increase. Industry players will have have a better, in preliminary, understanding of how Amazon will impact the fraud prevention market by early next year.
“Customers of all sizes and across all industries have told us they spend a lot of time and effort trying to decrease the amount of fraud occurring on their websites and applications,” said Swami Sivasubramanian, Vice President, Amazon Machine Learning, Amazon Web Services Inc. “By leveraging 20 years of experience detecting fraud coupled with powerful machine learning technology, we’re excited to bring customers Amazon Fraud Detector so they can automatically detect potential fraud, save time and money, and improve customer experiences—with no machine learning experience required.”