Fighting Fraud in a Rapidly Transforming Travel Industry

Like many sectors, travel is undergoing major digital-driven transformation. This is helping to drive customer engagement and growth on a scale never before seen. But while the internet has provided a new platform for airlines, hotels, travel agents and others to grow, it’s also exposing these same companies to increased fraud risks.

This is where the industry needs advanced, adaptive fraud decisioning tools that leverage the power of machine learning to mitigate risk and enhance assurance without adding friction to the customer journey.

A global phenomenon

Travel now accounts for a staggering percentage of global GDP. Online is increasingly key to driving value for firms operating in the sector. One source claims that digitalization created $305bn in value between 2015 and 2016, for example. Smartphone and mobile internet penetration in particular is opening up the industry for increasing numbers of consumers. The travel industry is ranked fifth globally in terms of mobile technology adoption, while related apps are one of the most popular categories in the Apple App Store.

Whether small online travel agencies (OTAs) or multinational aggregation sites, travel sector firms are being forced to respond to rising customer expectations to drive growth and retention. Modern tech-savvy travelers want more personalization and flexibility; they want to take advantage of experiences provided by the sharing economy, and they’re looking to be rewarded for their hard-won loyalty. They need online experiences to be intuitive, seamless and friction-free. But increasingly, they’re also looking for security and assurance, especially at the payment stage.

Fraud takes off

This is largely because fraudsters are increasingly making their presence felt in online travel. At Simility, we’ve seen a steady rise in fraud attempts over 2018, with scammers often looking to hide their efforts during peak periods. The most common fraud types are:

  • Payment: Scammers use stolen credentials to make unauthorized payments, resulting in high chargebacks.
  • Identity: Stolen or synthetic identities enable fraudsters to open new accounts.
  • Account takeover (ATO): Stolen credentials and/or brute force attacks allow scammers to hijack victims’ accounts, making it hard to detect subsequent transactions as fraudulent.

The majority of fraudulent bookings detected by Simility last year came from desktops (70.2%) as opposed to mobile devices (29.8%). This is because it’s easier for the bad guys to launch large-scale botnet-based attacks from the desktop. These automated scripts do the bidding of their masters, trying stolen credentials and/or multiple permutations of common passwords concurrently across numerous sites at high speed, in order to access accounts. Outdated operating systems like Windows 7 are especially at risk.

We found bots used in 15% of attacks. Other tell-tale indicators of fraud are identity spoofing attempts (23.7%), perhaps using anonymized proxies or masking software for smartphones. A sizeable number of fraud attempts (18.9%) we spotted were from repeat offenders.

Often, the fraudsters try to target multiple online services offered by a single platform provider — including flight and hotel bookings, car rentals and more. The challenge for the provider is to consolidate data from each service to spot fraud patterns. There’s also a fine balance to be had: if fraud screening is excessive it could add too much friction to the customer journey and operational overhead in the form of manual reviews. But too light-touch, and it may miss fraudulent transactions, driving up chargeback costs.

Digital peace of mind

The answer is to choose next-generation fraud prevention tools which combine data from multiple sources and apply machine learning models to generate a 360-degree view of each customer. With Simility’s best-in-class Adaptive Decisioning Platform, machine learning models can be manually updated by fraud experts to leverage in-house expertise. They also adapt over time as fraud evolves to spot complex fraud patterns that human eyes would miss, helping to automatically block suspect transactions.

When a leading OTA suffered from high chargeback costs and excessive manual reviews, significant customer friction and a time-consuming process for configuring its legacy fraud solution, Simility stepped in to add complex decision orchestration, accurate device recognition and link analysis —stabilizing chargeback rates to just 0.08% per month. The OTA is now able to automatically process 99.5% of bookings with minimal friction, and escalate when necessary for more accurate and speedy manual reviews. Analysts can easily change rules and maintain watch lists.

In a new era of digital opportunity, there are also new risks. Travel sector firms need to take extra steps with advanced fraud prevention to help protect the bottom line and corporate reputation.

To learn more about how Simility can help travel platforms fight fraud, download our eBook or schedule a demo now.

Rahul Pangam

Rahul Pangam

Rahul is the Co-Founder and CEO of Simility. Being a fraud detection industry veteran, he believes in combining the power of algorithms to recognize similar and dissimilar signals with the ability for humans to create meaning and giving front-line fraud fighters tools that empower them to put their domain expertise and knowledge to use without needing to write code.
Rahul Pangam