Traveloka is one of the fastest growing tech companies in Southeast Asia that provides travel booking services for domestic and international destinations. Traveloka focuses on helping customers book flights and hotels quickly, easily, and economically. With exclusive travel deals and no hidden fees, as well as real-time confirmations, Traveloka wanted a smart fraud solution that could reduce their fraud false-positive rate and keep their legitimate customers happy.
A travel case study
How Traveloka increased real-time bookings and cut false positives
Reduced false positives
Increased conversion rate
Improved customer experience
Told from the perspective ofWayan Tresna Perdana,Sr. Product Manager - User Platform
“Sift Science helps us to identify more good customers and reduce the number of transactions that have to be authenticated, thus reducing payment friction and increasing overall conversion.”
A smart booking platform for savvy travelers
Jakarta-based Traveloka is Indonesia’s number one platform for booking flights and getting great deals on hotels. With an ever-growing number of visitors to the site, this company has grown to offices in Thailand, Malaysia, Singapore, Vietnam, and the Philippines. Traveloka’s business is booming in the Southeast Asian market and – following on the heels of legitimate customers – fraudsters are creeping into the fold.
Less friction for good travelers
Although the volume of fraud on the platform is miniscule, the Traveloka team is committed to keeping that rate low as sales grow. The two main types of abuse that Traveloka sees are payment fraud – with stolen credit card numbers – and account takeover. In order to combat these problems, Traveloka dedicated an internal team to fraud and risk, developing a series of aggressive fraud rules that provided an automated first screening of all orders.
However, as the range of customers on the site changed, Traveloka began to experience false positives with their rules-based system. In order to maintain their low fraud rate while also reducing friction for legitimate customers falsely caught in the rules filters, Traveloka searched for a flexible and adaptive solution.
“When our anti-fraud rules rejected too many legitimate transactions, we engaged with Sift Science to reduce that number of false positives and stay ahead of real fraudsters.”
A fraud solution with fewer false positives
In keeping with Traveloka’s focus on smart solutions and innovation, they began investigating machine-learning based solutions. Big data was already an integral part of Traveloka’s customer service, marketing, and fraud operations. And now the product team – headed by Wayan Perdana – was tasked with finding an adaptive solution that not only reduced false positives, but could also increase conversions.
After working hand-in-hand with engineering to create a customized and fully functional integration, Traveloka had Sift Science set up and ingesting custom data fields. This data-driven approach quickly paid off with accurate results, which gave Traveloka the ability to reduce friction for legitimate customers and preemptively identify networks of bad users.
“We believe in an adaptive machine-learning approach to fraud management. Sift Science’s web interface and API were quite simple and straightforward.”
Faster checkout for happy customers
With accurate results in hand, Traveloka has been able to not only leverage Sift Science to reduce their number of fraud false positives, they have also increased their conversion rate. In addition to spotting fraudsters on the platform, the learnings from the Sift Science console have identified legitimate customers, allowing Traveloka to reduce friction for them and create a smooth and effortless checkout process.