Machine Learning platform for complete fraud and abuse prevention

Founded: 2011
HQ: San Fransicsco / United States

Sift, formerly Sift Science, is the leader in Digital Trust & Safety, empowering companies of all sizes to unlock revenue without risk. Sift dynamically prevents fraud and abuse with industry-leading ML technology and expertise, an unrivaled global data network, and a commitment to building long-term partnerships with its customers.

  • Financial Services
  • Ecommerce
Primary Functionality
  • Fraud Platform
Fraud Type
  • Payment Fraud
  • Account Takeover
  • New Account Fraud
  • Loyalty or Promo Abuse
  • Content Abuse
  • Behavioral Biometrics
  • Machine Learning

Reference Customer







Fraud Solution Profile

What we offer
Sift Science provides tools to minimize financial loss and brand damage from various fraud and abuse risks through one, user-friendly portal:

Payment Fraud:
Customers can eliminate credit card fraud, perform less manual review and increase revenue by detecting users at increased risks of conducting credit card fraud.

Content Abuse:
Helps customers stop bad actors from posting malicious or low-quality content that can deter site traffic.

Promo Abuse:
Customers can keep promo abusers from taking advantage of marketing programs and depleting budgets.

Account Abuse:
Helps customers prevent fake accounts from being created before their community integrity is compromised.

ATO Prevention:
Helps customers identify account takeover before bad users take fraudulent actions or steal information with a good user’s account.

How we work

Sift Science is the most comprehensive platform of fraud and abuse prevention products leveraging real-time and machine learning technologies.

Sift Science technology works similarly to how Google uses machine learning to fight spam. Gmail users flag spam-y emails and Google learns what traits are associated with those spam-y emails. Google uses this information to automatically detect and filter emails that exhibit spam-like qualities. This results in less spam reaching inboxes of Gmail users.

While Gmail users flag spam, Sift Science customers quickly integrate our intuitive desktop and mobile APIs and so we can ingest their data points to identify fraud. Apps and websites worldwide send data about their online community interactions in real time using Sift Science’s REST APIs, JavaScript snippet, and mobile SDK. Then, fraud analysts can flag fraudulent or abusive users or transactions for the Sift Science system to analyze.

Sift Science analyzes company data and fraud/abuse flags instantly, connecting thousands of seemingly unconnected clues to identify fraud and abuse. We are the only fraud prevention platform that learns from user actions on a site right when they happen.

On their console, customers see scores generated from this data that predict how risky a potential user is. Scores can be applied to payment fraud, account, content/marketplace, ATO and promo abuse.

Customers can then decide how to follow up with users of different scores. Analysts can use the Sift Science console to investigate fraud associated with risky scores or create smart workflows to automate responses to users of different scores.

Sift Science customers save time and money by preventing fraud, creating operational efficiencies, and reducing the need for manual review. At the same time, these businesses also reduce friction, increase conversion rates, and grow revenue by using Sift Science to identify legitimate, trusted users and optimizing their experience.

Share this page: