Communications of the ACM
Companies Beef Up AI Models with Synthetic Data
According to an industry report, American Express has had the lowest U.S. fraud-loss rates among the major banks for the past 14 years. It is experimenting with supplemented artificial data to bolster its AI models in detecting rare frauds.
Credit: Brendan McDermid/Reuters
Companies are building synthetic datasets when real-world data is unavailable to train artificial intelligence (AI) models to identify anomalies.
Dmitry Efimov at American Express (Amex) said researchers have spent several years researching synthetic data in order to enhance the credit-card company's AI-based fraud-detection models.
Amex is experimenting with generative adversarial networks to produce synthetic data on rare fraud patterns, which then can be applied to augment an existing dataset of fraud behaviors to improve general AI-based fraud-detection models.
Efimov said one AI model is used to generate new data, while a second model attempts to determine the data's authenticity.
Efimov said early tests have demonstrated that the synthetic data improves the AI-based model's ability to identify specific types of fraud.
From The Wall Street Journal
View Full Article - May Require Paid Subscription
Abstracts Copyright © 2021 SmithBucklin, Washington, DC, USA
No entries found