Sift Logo Several blue dots forming a sphere to the left of the word Sift in italic font.
  • Products

    Digital Trust & Safety Suite

    Fight fraud without sacrificing growth

    Learn more →

    Passwordless
    Authentication

    Account
    Defense

    Content
    Integrity

    Payment
    Protection

    Dispute
    Management

    Sift
    Connect

    PSD2
    Solution

    New Releases & Enhancements

  • Partners

    Sift Partner
    Program

    Join the leader in Digital Trust & Safety

    Learn more →

    Commerce platform partners


  • Industries

    One solution, many applications

    Learn how Sift can work for your industry

    Learn more →

    Featured industries


    Fintech

    Retail

    Food & Beverage

  • Customers

    See case studies by industry

    Sift works across every use case and region

    Learn more →

    Featured customers


  • Resources

    Explore our resources

    Access trends, guides, and insights from Sift

    Learn more →

    Blog

    Ebooks

    One Pagers

    Demos

    Videos

    Webinars

    Infographics

    Podcasts

    Trust & Safety University

  • Fraud Center
  • Company

    Why leaders choose Sift

    Technology, community, and partnership

    Learn more →

    Our mission: Help everyone trust the internet


    About

    Careers

    News & Press

Request a demo
Products
  • Digital Trust & Safety Suite
  • Passwordless Authentication
  • Account Defense
  • Content Integrity
  • Payment Protection
  • Dispute Management
  • Sift Connect
  • PSD2 Solution
  • New Releases & Enchancements
Why Sift
  • Salesforce
  • Magento
  • Shopify
Industries
  • Fintech
  • Retail
  • Food & Beverage
Customers
Resources
  • Blog
  • Ebooks
  • One Pagers
  • Demos
  • Videos
  • Webinars
  • Infographics
  • Podcasts
  • Trust and Safety University
Fraud Center
About
  • Search Careers
  • Our Company
  • Contact Us
  • Engineering Blog
Request a DemoSign In
  • Blog Home
  • Fraud
< prev / next >
Share this article on LinkedIn
Tweet this article
Share this article on Facebook
SOCIALICON
Share this article via email

The First Rule in Fighting Fraud: Rules Can Fail

By Bill Hodak  / 

23 Jan 2015

If you’ve ever seen the movie Fight Club, then you know that the first rule of Fight Club is, “You do not talk about Fight Club.”  The second rule of Fight Club is, “You do not talk about Fight Club.” Apparently, they didn’t trust that people would follow the first rule, so they made the second rule the same as the first.  While I’m not sure that doubling the rule would actually doubly enforce the rule, it did effectively send the message that Fight Club members were forbidden to talk about Fight Club.

Fight Club Wallpaper courtesy of Jessica Pereira, on Flickr
Fight Club Wallpaper courtesy of Jessica Pereira, on Flickr

When it comes to the Fraud Fighting Club, the first rule is, “Rules fail.” Channeling my inner Brad Pitt, I will also say that the second rule of Fraud Fighting Club is, “Rules fail.”

So why don’t rules work when fighting fraud? First, let’s define what we mean by rules. The first generation of online fraud management systems were essentially rule-based engines or systems that allowed fraud managers to manually compile a list of static if-then statements that defined whether to consider an order “good” (and process normally) or whether to consider an order “bad”.  If the order was “bad”, then the fraud management system could either block the order or send it over to the fraud team for further review.

On the surface, rule-based systems seem pretty effective at detecting and preventing fraud. However, let’s take a look at an example to understand the inherent flaws of using rules to fight fraud:

Let’s say someone tries to buy shoes online from vendor We Sell Shoes Online and the customer order information reveals that the customer’s last name is “Fraudster” and he is trying to purchase a pair of kicks for $199.

Unfortunately, We Sell Shoes Online experienced fraud in the past from someone with the last name “Fraudster”. In response, they created a rule that automatically blocks all orders from customers with the last name Fraudster. Boom – problem solved, right?

Not so fast.  As it turns out, the last name “Fraudster” is actually quite common and this particular shopper was actually a good customer!  And because his order was blocked, Mr. Fraudster took his business to competitor We Sell Shoes Online Cheaper.

When Mr. Fraudster checked out with his $179 order from We Sell Shoes Online Cheaper – his purchase went through in no time and he saved a $20. Looks like We Sell Shoes Online Cheaper just got themselves a repeat customer!

Did We Sell Shoes Online Cheaper take on more risk? Not at all. They use a new technology to fight fraud called Machine Learning. With this powerful technology, they are able to proactively analyze thousands of attributes about each and every order in real-time. They too have experienced fraud from people with the last name “Fraudster”. But based on other attributes about the above example’s specific order (e.g. shipping and billing addresses, number of users per device, structure of the email address, etc.), their Machine Learning technology identified that this was in fact a good order.

Now imagine that another customer tries to buy the same shoes from We Sell Shoes Online and his last name is “Fraudster123”.  Since We Sell Shoes Online never previously encountered a customer with that last name, they process the order quickly and a month later get a chargeback because this guy used a stolen credit card. Dang it – rules failed again!

Mr. Fraudster123, feeling confident from successfully stealing from We Sell Shoes Online, decides to try his luck again – this time buying shoes from We Sell Shoes Online Cheaper. Lo and behold, nobody with the last name of Fraudster123 previously purchased from We Sell Shoes Online Cheaper either. However, our merchant blocks Mr. Fraudster123’s order immediately.  Why? Because their Machine Learning technology analyzed other attributes about this order – not just the customer’s last name. And as it turns out, there were many red flags, clearly marking this order as fraudulent.  For example, We Sell Shoes Online Cheaper customers with a last name ending in 123 are 90% more likely to be fraudsters. This data, plus thousands of other signals, gave We Sell Shoes Online Cheaper the information they needed to block this order with confidence.

Let’s tally up the results:

We Sell Shoes Online just lost $998:

– $199 (by canceling a good customer’s order)
– $199 (by selling shoes to a fraudster)
– $100 (chargeback fee due to fraudulent activity)
– $500 (future lost revenue from losing a good customer)

We Sell Shoes Online Cheaper just earned $679 and saved $279 for a total gain of $958:

+ $179 (for selling shoes to a good customer)
+ $500 (future revenue from gaining a good customer)

Saved: $179 (for not selling shoes to a fraudster)
Saved: $100 (for not getting a chargeback fee)

It’s pretty clear that We Sell Shoes Online Online Cheaper did a better job of fighting fraud and providing good service to good customers.  And they made more money while doing it. Triple Bonus! Now, you must be thinking to yourself, “I want to be like We Sell Shoes Online Cheaper, but Machine Learning sounds awfully complicated and I’m sure it’s ridiculously expensive.”

That’s where we come in. Sift Science has created the world’s best fraud prevention system based on our advanced machine learning technology. Learn more about Sift Science and Machine Learning at siftscience.com!

Related

Bill Hodak

Bill Hodak was the Head of Marketing at Sift.

  • < prev
  • Blog Home
  • next >
Company
  • About Us
  • Careers
  • Contact Us
  • News & Press
  • Partner with us
  • Blog
Support
  • Help Center
  • Contact Support
  • System Status
  • Trust & Safety University
  • Fraud Management
Developers
  • Overview
  • APIs
  • Client Libraries
  • Integration Guides
  • Tutorials
  • Engineering Blog
Social

Don't miss a thing

Our newsletter delivers industry trends, insights, and more.

You're on the list.

You can unsubscribe at any time. Please see our Website Privacy Notice.

If you are using a screen reader and are having problems using this website, please email support@sift.com for assistance.

© 2022 Sift All Rights Reserved Privacy & Terms

Your information will be used to contact you about our service and subscribe you to our direct marketing communications. You can, of course, unsubscribe at any time. Please see our Website Privacy Notice.