Fraud Detection for Online Retail using Random Forests

As online commerce becomes more common, fraud is an increasingly important concern. Current anti-fraud techniques include blacklists, hand-crafted rules, and review of individual transactions by human experts. These methods have achieved good results, but a significant number of costly fraudulent transactions still occur, and the fraud detection process is expensive due to its heavy reliance on human experts. Our goal is to improve the quality of fraud detection and decrease the need for costly human analysis of individual transactions. We propose two modifications to the approval process for an online retailer based on a Random Forests classifier.