Jason Tan, Sift Science: "Sift takes a no rules, just data approach to ecommerce fraud"

Jason Tan (@jasontan) is the Co-Founder and CEO of Sift Science, a San Francisco technology company that fights online fraud with large-scale machine learning. He previously served as CTO of BuzzLabs, a machine learning startup acquired by InterActiveCorp. Prior to that, he was an early engineer at two Seattle startups, Zillow and Optify. Jason graduated magna cum laude from the University of Washington in 2006 with a Computer Engineering degree.

Sift Science is a US-based technology company dedicated to making world-class fraud detection accessible to everyone. Sift designed its automated, real-time, large-scale machine learning solution to make finding and stopping online fraud as quickly, easily, and accurately as possible. Comprised of a multidisciplinary team of innovators, Sift Science has the backing of investors like: Spark Capital, Union Square Ventures, First Round Capital, PayPal co-founder Max Levchin, Salesforce CEO Marc Benioff, Zillow co-founder Rich Barton, angel investor Chris Dixon, Y Combinator, and other well-versed in e-commerce, payments, and fraud ones. For more information about Sift Science, visit us at siftscience.com.

What is Sift Science’s approach when it comes to ecommerce fraud?

Jason Tan: Sift takes a “no rules, just data” approach to ecommerce fraud. We’ve built our product to be:
• Accurate: Accurate scores mean great results. Our goal is to have Sift customers catch all of their fraud with very low false positive rates.
• Fast: Sift’s learning and analysis work in real time. Fraud scores are available immediately and updated continuously to incorporate customer feedback as soon as it’s given. With Sift, our customers never need to set rules.
• Comprehensive & customized: With large-scale machine learning, Sift leaves no stone unturned in looking for fraud patterns. Sift users get their very own Sift models that adapt to each unique business; by combining our existing fraud library with each store or website’s data, every customer’s Sift model is specially-tailored to his or her needs. For example, if a customer sells shoes, we might learn that size 10 shoes are more suspicious than size 15 shoes.
• Transparent: Scores and signals are available to customers via our real time console, APIs and email notifications, so the information is available whenever and wherever you need it. Our console is a one-stop shop; there, users can find all of the information that a fraud team requires to streamline decisions as well as view data visualizations to better understand customer patterns and actions.
• Easy: With Sift, it’s easy to get started and there’s no risk to try our fraud-fighting product. Integration is simple and we require no contract lock-in or setup fees. Every customer gets a 30-day free trial. Our pricing structure is transparent and designed to support every customer’s growth.

The online environment as well as the payments industry are changing at a faster pace. What is the impact this constant development has on online security?

Jason Tan: Online security companies are subject to intense pressure because online payments and ecommerce opportunities continue to rapidly evolve. This environment requires a two-fold response:
1) Solutions must be flexible & adaptive (whether to new business models, or to the ways that consumers can spend money): Models must be customized to the unique and constantly changing methods that fraudsters use when attacking a customer’s site. Strength comes in the ability to learn from and predict the unique patterns seen in a vertical, business model or geography. Online security companies must leave no stone unturned and adapt to even the most sophisticated fraudster’s tactics.
2) Solutions must be comprehensive and work in real time: The payments industry must be able to analyze all available data and discover all available patterns in real time. Best-in-class technology is essential in order to stay ahead of fraudsters.

Cybercrime attempts have increased lately, with more and more companies being targeted. What could they do to stay ahead of security risks?

Jason Tan: We all need to take a proactive approach to fraud prevention and leverage the fraud patterns seen globally across the internet. For example, fraud patterns displayed in the gaming industry often show up in other industries years later. Companies can stay ahead of these risks by getting access to pooled learnings. For example, Sift Science has a library of 5M fraud patterns that our customers can leverage and apply their fraud-finding models.

What are the biggest challenges when it comes to payment security for retailers and customers nowadays?

Jason Tan: Although fraudsters are growing more sophisticated, the data that retailers need to protect themselves from fraudsters is available and always increasing. However, taking advantage of it - e.g. collecting, processing, and deriving insights from this data -- is incredibly difficult. The technology exists, but the skills required to execute on the intricacies of the technology are scarce and, usually, are only found at places like Amazon, Paypal, and Google. At Sift, we’re making this state-of-the-art technology accessible and offering our customer lessons learned on a global scale.