{"id":1507,"date":"2022-01-27T17:51:01","date_gmt":"2022-01-27T17:51:01","guid":{"rendered":"https:\/\/salarydistribution.com\/machine-learning\/2022\/01\/27\/how-clearly-accurately-predicts-fraudulent-orders-using-amazon-fraud-detector\/"},"modified":"2022-01-27T17:51:01","modified_gmt":"2022-01-27T17:51:01","slug":"how-clearly-accurately-predicts-fraudulent-orders-using-amazon-fraud-detector","status":"publish","type":"post","link":"https:\/\/salarydistribution.com\/machine-learning\/2022\/01\/27\/how-clearly-accurately-predicts-fraudulent-orders-using-amazon-fraud-detector\/","title":{"rendered":"How Clearly accurately predicts fraudulent orders using Amazon Fraud Detector"},"content":{"rendered":"
\n

This post was cowritten by Ziv Pollak, Machine Learning Team Lead, and Sarvi Loloei, Machine Learning Engineer at Clearly. The content and opinions in this post are those of the third-party authors and AWS is not responsible for the content or accuracy of this post.<\/em><\/p>\n

A pioneer in online shopping, Clearly launched their first site in 2000. Since then, we\u2019ve grown to become one of the biggest online eyewear retailers in the world, providing customers across Canada, the US, Australia, and New Zealand with glasses, sunglasses, contact lenses, and other eye health products. Through its mission to eliminate poor vision, Clearly strives to make eyewear affordable and accessible for everyone. Creating an optimized fraud detection platform is a key part of this wider vision.<\/p>\n

Identifying online fraud is one of the biggest challenges every online retail organization has\u2014hundreds of thousands of dollars are lost due to fraud every year. Product costs, shipping costs, and labor costs for handling fraudulent orders further increase the impact of fraud. Easy and fast fraud evaluation is also critical for maintaining high customer satisfaction rates. Transactions shouldn\u2019t be delayed due to lengthy fraud investigation cycles.<\/p>\n

In this post, we share how Clearly built an automated and orchestrated forecasting pipeline using AWS Step Functions<\/a>, and used Amazon Fraud Detector<\/a> to train a machine learning (ML) model that can identify online fraudulent transactions and bring them to the attention of the billing operations team. This solution also collects metrics and logs, provides auditing, and is invoked automatically.<\/p>\n

With AWS services, Clearly deployed a serverless, well-architected solution in just a few weeks.<\/p>\n

The challenge: Predicting fraud quickly and accurately<\/h2>\n

Clearly\u2019s existing solution was based on flagging transactions using hard-coded rules that weren\u2019t updated frequently enough to capture new fraud patterns. Once flagged, the transaction was manually reviewed by a member of the billing operations team.<\/p>\n

This existing process had major drawbacks:<\/p>\n