SLA Digital Shapes the Future of Secure Transactions with Amazon Fraud Detector

Headquartered in the UK and Malaysia, SLA Digital creates new revenue streams for mobile operators and online merchants around the world through seamless and secure carrier billing solutions.

Carrier billing is a mobile payment method for consumers to make online purchases by charging to their mobile bill or using prepaid credit. SLA Digital provides a carrier billing platform that enables merchants to easily connect with mobile operators; reducing costs, operational risks, and time to market for both parties. The company’s mobile operator clients across Europe, the Middle East and Asia include Telenor Group and Zain Group, whose global subsidiaries benefit from carrier billing services delivered via SLA Digital’s platform.

As a payment aggregator, identifying and preventing fraudulent transactions is crucial to SLA Digital’s business. In 2017, the company saw a rise in the volume and sophistication of ecommerce fraud affecting mobile operators. This included payment fraud and the use of malware that automatically extracts information from users’ mobile phones.

To better protect mobile operators and improve customer experience on its carrier billing platform, SLA Digital worked with Amazon Web Services (AWS) to boost its fraud prevention capabilities with Amazon Fraud Detector, a fully managed service that uses machine learning to identify potentially fraudulent activity.

SLA Digital’s engagement with AWS started when it began developing its carrier billing platform. The company moved its DevOps workloads to Amazon Elastic Compute Cloud (EC2) to easily secure and resize its compute capacity in the cloud. With AWS’s support in developing a proof-of-concept, SLA Digital developed, tested, and deployed its carrier billing platform without adding more manpower or physical infrastructure.

In 2020, AWS showed SLA Digital how Amazon Fraud Detector helps shore up anti-fraud defenses. Subsequently, the company worked with AWS to develop a proof-of-concept using its own datasets to run, test, and finetune the machine learning model to achieve better results. Within six months, SLA Digital rolled out a new fraud detection feature in February 2021 that accurately identified instances of fraud with minimal false positives to maintain a high-quality mobile user experience.

The company reduced the number of fraud-related complaints from mobile operator customers significantly over the next six months. Richard Fisher, head of technology at SLA Digital, explains how Amazon Fraud Detector’s user-friendliness is ideal for his team.

“Twelve months ago, we were looking for a fraud detection solution that didn’t require us to invest heavily in our own machine learning expertise. With transparent pay-as-you-use pricing, Amazon Fraud Detector helped us easily create and incorporate an effective and affordable new machine learning model into our existing setup,” says Fisher.

A cloud-based architecture allows SLA Digital’s development team to focus on building code fast – without needing to manage databases and backups or source physical components. Yam Wai Kuan, cloud architect at SLA Digital, shares, “With a single configuration, Amazon Fraud Detector automatically trains the machine learning model for us, reducing development time for each fraud detection model from months to weeks.”

SLA Digital uses Amazon QuickSight to embed machine learning-powered business intelligence analytics into its services and glean insights on customer behavior that help merchants increase their conversions. This service is connected seamlessly to Amazon Simple Storage Service (Amazon S3) and Amazon Redshift, a cloud data warehouse, to run analytics workloads for about 26 GB of data daily.

The company also taps on Amazon Elastic Block Store (EBS), a high-performance, block-storage service with built-in key management that encrypts its data at rest, in transit, and all volume backups, to boost data security.

Fisher states, “The support from AWS – from training to ongoing service development and new features – is exceptional and we’re very happy with the results achieved so far. We’re excited to continue to expand our use of Amazon Fraud Detector as we grow our business and product offerings with more advanced security features.”

To learn more, visit Telecommunications on AWS