Telesign's Verify API leverages artificial intelligence and ML to enable omnichannel growth

Omnichannel sales have become desktop currency for any organization hoping to scale, which underscores the importance of protecting customer identities and combating fraud. Protecting identity and omnichannel revenue is a growing and complex challenge for all online merchants and e-commerce businesses.

Attackers ranging from malicious hackers to nation states are using generative artificial intelligence to take their craft to the next level and defraud online retailers and their customers on a large scale.

A major factor driving adversaries to intensify their attacks is the rapid growth in omnichannel and e-commerce sales. In 2023, e-commerce sales reached $5.8 trillion and are projected to grow at a 39% CAGR, surpassing $8 trillion by 2027. Omnichannel sales is one of the fastest growing areas of retail e-commerce, accelerated by artificial intelligence-based personalization of shopping.

Merchant losses from online payment fraud are expected to exceed $362 billion between 2023 and 2028. Global business-to-consumer (B2C) e-commerce fraud losses are expected to grow at a compound annual growth rate (CAGR) of more than 40% from 2023 to 2028.

Join enterprise leaders in San Francisco July 9-11 at our flagship AI event. Network with peers, explore the opportunities and challenges of generative AI, and learn how to integrate AI applications into your industry. Register

Omnicanals are under siege

The more successful the fraud attack, the more damage it does to the brand. E-commerce fraud destroys brands, goodwill and trust, driving customers away from competitors. CIOs and CIOs must ensure that ecommerce fraud is properly detected and responded to. According to Telesign, 94% of customers believe companies are responsible for protecting their digital privacy.

Sift has found that cybercriminals and fraudsters are relying on artificial intelligence and advanced automation techniques that democratize access, resulting in new Fraud-as-a-Service offerings. One of the most prominent and highly subscribed is FraudGPT. Fraud schemes are becoming so pervasive that 24% of respondents said they have seen offers online to participate in account takeover schemes. Sift also found that 73% of consumers believe a brand is responsible for ATO attacks and is responsible for protecting credentials.

Telesign's Trust Index shows that 44% of those affected by the data breach advise friends and family not to contact the leaked brand, and 43% refuse to do business with it. To make matters worse for brands affected by data breaches, 30% of customers share information about the incident on social media, further amplifying the impact of the incident.

Fighting online fraud with smarter APIs

Trading operations of malicious actors are gradually becoming more efficient through a combination of artificial intelligence, ransomware-as-a-service, and fraud kits including FraudGPT that are available on the dark web. Strengthening application programming interfaces (APIs) with a combination of AI and machine learning (ML) can reduce fraud by protecting identities and transactions across multiple validation channels.

An AI and OD approach to adding contextual intelligence to APIs and consolidating omnichannel verification traffic into a single API simplifies transactions and reduces fraud risks. Telesign has long noticed the need for AI-enabled APIs that could unify verification channels, and began working on the idea with its customers. Within months, what started as a customer-driven concept evolved into the Verify API.

In a recent interview with VentureBeat, Telesign CEO Christophe Van de Weyer talked about how the company is using AI and ML to build Intelligence APIs. "Machine learning allows us to continuously learn fraud behavior. It can learn typical user behavior to create baselines and build risk models. At Telesign, our Intelligence API, which can be paired with the Verify API, uses AI to analyze phone numbers, email addresses, IP addresses, and more."

When asked how Telesign leverages its expertise in using phone numbers to verify identities in conjunction with AI/ML, Van de Weyer said, "It helps identify red flags based on activity and phone number patterns. It looks for anomalous behavior by analyzing call speed and duration, including looking at call patterns and usage to help flag risky numbers. This process underpins the risk recommendations and scores that the Intelligence API produces, which can be used by the customer to better understand when to strengthen authentication processes."

Why the Telesign Verify API is defining the future of omnichannel verification

Brandon O'Donovan, VP of GTM Strategy at Telesign, talked about how the Verify API leverages Telesign's machine learning expertise in a recent interview with VentureBeat. "The Verify API works with our AI machine learning products, and we're constantly working to find new out-of-the-box ways to enable it and recommend whether you want to risk check that phone number before sending an OTP (one-time password)."

Telesign's Verify API is notable because it is the first omnichannel API to incorporate a broad base of artificial intelligence/ ML algorithms to reduce fraud risk, improve identity security, and reduce verification costs.

Here are the key areas that define how the Verify API is shaping the future of omnichannel verification and e-commerce:

• Integrate with seven leading user verification channels and select the best channel based on cost, experience and reliability by country or region:SMS, Silent Verification, Push, Email, WhatsApp, Viber and RCS (Rich Communication Services) into a single API. With a single integration, Telesign's Verify API allows companies to easily scale new authentication channels with minimal development resources.
• Support for AL and ML algorithms across all APIs provides real-time response to any omnichannel transaction and identity verification:AI and machine learning are integral components of Telesign's new Verify API as they enhance the platform's anti-fraud capabilities and provide secure identity verification.
• Risk assessment and fraud detection provided in the new API library:Telesign's Verify API works in conjunction with machine learning artificial intelligence products, such as Intelligence, to produce a phone number reputation score. This score is generated from machine learning algorithms that analyze global traffic patterns, phone data attributes, and comprehensive information about the phone number. By evaluating these factors, the system can recommend fraud risk and identify unusual patterns that may indicate fraudulent activity.
• Anomaly detection based on device attributes : The AI in Verify API can detect anomalies based on device attributes. For example, suppose a phone number has been recently ported to a new device or a sim card has been changed. In this case, the system can flag this as high risk and take appropriate action, such as not sending an OTP or requiring additional verification steps.
• Determining friction levels and communication channels : Companies use AI to determine the appropriate level of friction for a particular transaction based on a risk assessment. This means that for high-risk transactions, an organization can introduce additional validation steps. Conversely, for lower risk interactions, the process can be simplified to improve the user experience.
• Integration with existing fraud models : Telesign APIs can integrate with a company's internal fraud models using artificial intelligence to improve protection against synthetic identity fraud, IRSF attacks, promotion abuse, etc. This integration allows for more comprehensive protection against different types of fraud.

The vision of the Verify API is to provide cost-effective and secure multichannel messaging at scale.

During an interview with VentureBeat, de Weyer emphasized the dual nature of using AI/ML as a core part of the Verify API architecture. Reducing fraud risk and protecting identities is one thing, but reducing the cost per message is another.

De Weyer told VentureBeat last week that "SMS messaging is ubiquitous and low cost, but companies that spend a lot of it can face increasing and often unpredictable costs per message depending on the country (or countries) they are in. With the Verify API, customers can select primary and backup channels by destination, which helps control costs, improve the customer experience, and deliver messages on the preferred channel in a given country or region."

When asked how these innovations are delivered to customers through the Verify API, Van de Weyer said: "Customers can use the Verify API to configure verification and authentication across multiple channels such as WhatsApp, Push or email to achieve a more stable cost structure and a more secure experience. SMS is still a common fallback if and when the preferred channel fails. The overall goal is a more robust cost structure, better customer experience and less fraud, regardless of the geographic location of the customer."