Layer 1 copy

Sift enabled us to make the user buying experience more friendly and frictionless allowing us to provide a better user experience.

Tal Yeshanov Payments & Risk Manager

Overview

  • Online dating business with 35 million members

  • Available in 80+ countries and 25 languages

  • Real-time and behavior-based matching

Challenge

  • Payments and friendly fraud on the site

  • In-house solution couldn't scale

Solution

  • Flexible and real-time machine learning

  • Direct integration into existing fraud management system

Results

  • Improved user experience

  • Streamlined fraud management flow

Overview

Connecting members in real time

As a leading online dating company that learns as you click, Zoosk seeks to pair you with singles with whom you're likely to discover mutual attraction. Zoosk's Behavioral Matchmaking technology is constantly learning from the actions of its 35 million members. With the #1 grossing online dating app in the Apple App Store, Zoosk is a market leader in mobile dating. Available in over 80 countries and translated into 25 languages, Zoosk is a global online dating platform.

Challenge

Breaking up with bad users

As a social network and marketplace, Zoosk strives to provide users a positive online experience, and fraudulent users can spoil the experience for the legitimate ones. There is no fee to join Zoosk, but for members who want to use Zoosk's full communications platform, Zoosk offers users paid subscriptions.

When Zoosk's Payments & Risk Manager, Tal Yeshanov, joined the team, Zoosk was already working to reduce friendly fraud and payments fraud on the site. The dedicated team tasked with tackling fraud for Zoosk used a variety of tools and processes to manage fraud. But the real-time nature of Zoosk's service and their ever-expanding user base meant that the company needed a solution that could adapt instantly and scale as their business grew. Ready for a change, Tal connected with the Sift Science team.

Solution

Finding the perfect match

Even before becoming a member of the Zoosk anti-fraud team, Tal had already done her research on the most effective methods of fighting fraud. When faced with Zoosk's need for an adaptive and accurate fraud solution, she knew that machine learning was the key. With the fluidity of fraudster behavior, Zoosk had to not only address existing bad users but also try to prevent their return.

Sift enabled us to make the user buying experience more friendly and frictionless allowing us to provide a better user experience.

Tal turned to Sift Science's big data and real-time solution, which empowered her fraud analysts with ever-updating intelligence. By integrating Sift Science's findings via Sift Score API into Zoosk's existing management system, the team now has more data and is more efficient.

We've seen Sift's accuracy improve as we've continued to use the solution.

Results

A happy relationship with Sift Science

Since implementing Sift Science, Zoosk has streamlined their fraud management workflow. With the fraud team's increasingly efficient review process, Zoosk is able to offer members an even better experience. Sift Science's real time machine learning model enables us to get accurate data quickly, thus allowing us to make informed decisions in real time. Tal's team can use the Sift Score and Sift Science's easy and intuitive tools to block users and investigate suspicious behavior. Layering Sift Science on top of their other tools helps Zoosk keep its focus on the best ways for its users to connect and find great dates.

We were using different systems and now all of them are in the same place – Sift Science has allowed us to update and streamline our solutions and is giving us real results.