Payments solutions provider Vesta today announced that it raised $125 million in capital, bringing its total raised to over $145 million. The company says it will use the financing to grow and accelerate the deployment of its fraud protection and ecommerce payment products.

Payment fraud is pervasive — in 2018, $24.26 billion was lost due to credit card fraud worldwide, reports Shift Processing. That same year, the rate of card fraud increased by nearly 20% as the U.S. took the lead in reported losses. Vesta says its AI-powered decisioning platform helps clients to assess the risk of this fraud and ultimately to prevent fraud from occurring, with connectors that tie into existing software from vendors including Magento, Shopify, WooCommerce, BigCommerce, and SAP Commerce Cloud.

Alpharetta, Georgia-based Vesta, which was founded in 1995, initially focused on processing fully guaranteed card-not-present payment transactions for the telecommunications industry. It subsequently expanded to new verticals, and it now claims to process billions of dollars in payments annually with AI trained on 2 trillion data points (e.g., phone numbers, addresses, device identifiers, geographic locations, ZIP codes, and over 292 million credit card numbers).

Vesta provides an API through which customers can send real-time transaction data including order, cardholder, and session information. On the backend, machine learning models make decisions informed by behavioral analytics, merchant and third-party vendor preferences, and features teased out by Vesta’s data scientists. Transaction details and other signals not available at payment time are collected and stored in a secure database, allowing Vesta’s analysts to spot fraud and retrain the models. Those analysts also select samples of transactions, ensuring the models are working as trained, and at the same time investigating alerts to continuously improve their performance.

VB Transform 2020 Online - July 14-17. Join leading AI executives: Last chance to register!

Vesta offers payment protection, payment guarantees, and account protection services, among others. On the payment protection side, the platform delivers a score that can be used to evaluate transactions in less than a second. With respect to payment guarantees, Vesta handles fraud detection, manual reviews, and chargeback representations, with real-time reporting and transaction views through an online portal. And to prevent account takeovers, Vesta says it monitors login attempts or adjustments to account information (like password reset attempts, settings and email address changes, and bank account additions) by comparing device fingerprints, biometric patterns, browser data, and keylogger events with those of known and similar user profiles.

Vesta supports payments across a range of devices and types, including web, mobile, tablets, phones, debit cards, prepaid cards, and Apple Pay, and it offers a pre-authorization decisioning service that protects transactions during the ecommerce checkout process. The company says that on average, its solutions raise transaction approval rates by 10%.

The global fraud detection and prevention market is anticipated to reach $23.3 billion this year, according to Grand View Research, and Vesta isn’t the only player vying for a slice. Two years ago, PayPal acquired AI-powered fraud detection startup Simility for $120 million. Sift Science meshes big data and machine learning to spot patterns and detect fake accounts, payment fraud, account takeover, and content abuse. Socure is developing a range of cloud-based identity verification and fraud prevention solutions. Others include Singapore-based CashShield; Tel Aviv-based Forter; Paris-based Shift Technology; U.K.-based Featurespace; and Atlanta-based Pindrop, which counts Google Capital among its investors.

But Vesta’s stable of high-profile customers — which includes AT&T, T-Mobile, Vodafone, WesternUnion, Claro, and Movistar — arguably gives it a leg up.

Private equity firm Goldfinch Partners led this latest investment in the company.