• Products

    Digital Trust & Safety Platform

    Fight fraud without sacrificing growth

    Learn more

    Platform solutions

    • Payment Protection
    • Account Defense
    • Dispute Management
    • Content Integrity
    • Sift Connect

    Sift innovations

    • PSD2 Solution
    • New Releases & Enhancements
  • Industries

    One solution, any industry

    Learn how Sift can work for your industry

    Learn more

    Featured Industries

    • Fintech
    • Payment Service Providers
    • Retail
  • Customers

    Case studies by industry

    See how leading brands succeed with Sift

    Learn more

    Featured Customers

    • DoorDash
    • Uphold
    • Paula’s Choice
  • Partners
  • Fraud Center
  • Resources

    Live webinars & events

    Industry conferences and live sessions

    Learn more

    • Blog
    • Demos
    • Infographics
    • Ebooks & Reports
    • Videos
    • Podcasts
    • One-Pagers
    • On-demand webinars
    • Trust & Safety University
  • Company

    Why leaders choose Sift

    Technology, community, and partnership

    Learn more

    Our mission: Help everyone trust the internet

    • About
    • Careers
    • News & Press
    • Live events
Talk to an expert
Products
  • Digital Trust & Safety Platform
  • Payment Protection
  • Account Defense
  • Dispute Management
  • Content Integrity
  • Sift Connect
  • PSD2 Solution
  • New Releases & Enhancements
Industries
  • Fintech
  • Retail
  • Payment Service Providers
Customers
Partners
Fraud Center
Resources
  • Live webinars & events
  • Blog
  • Ebooks & Reports
  • One-Pagers
  • Demos
  • Videos
  • On-demand webinars
  • Infographics
  • Podcasts
  • Trust and Safety University
Company
  • Search Careers
  • Our Company
  • Contact Us
  • Engineering Blog
Talk to an expert Sign 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

Machine learning for poets

By Stephanie Yee  / 

July 23, 2013 Updated July 22, 2022

This article is the first in a series that explains, in simple terms, what machine learning is. It is geared toward non-technical folks (like me). Later, we’ll discuss more advanced examples, technical challenges, etc.

What is machine learning? You may not have a crisp definition, but it’s a technology you experience daily. Whether browsing Netflix movie recommendations, having a heart-to-heart with Siri, or navigating the interwebs with Google, you’re witnessing machine learning’s unique power.

Today, we’ll talk about the branch of machine learning often used for fraud detection — supervised machine learning — and show how it’s applied to spam detection.

What is supervised machine learning? An answer in 60 words

Supervised machine learning is a technology where computers:

  • Train a model: Analyze and determine how to categorize past instances
  • Apply the model: Categorize current instances
  • Improve the model: Get and adapt to feedback on those categorizations

Like puppies, employees, or spouses, supervised machine-learning models improve with feedback. High-quality supervised machine learning is difficult to develop but can be easy and cost-effective to deploy.

Machine learning made tangible: Spam filtering

Ten years ago, I systematically abandoned email accounts because of excessive spam. Spammer sophistication made setting manual filters a Sisyphean chore. Were I not overwhelmed by spam, I’d have marveled at the creativity required to find infinite spellings of “Viagra” or “weight loss.”

In 2001, AOL said spam is the “No. 1 complaint of its subscribers”

Enter Google’s Gmail, which applies supervised machine-learning to spam filtering:

  • Train: A new Gmail account has its own spam model, trained by emails from other Gmail users.
  • Apply: The model categorizes incoming emails as spam or not-spam, based on subtle signals like the number of exclamation points or the frequency of the word “free.”
  • Improve: If the model makes a mistake, you mark bad email as spam (or vice versa). The model incorporates your and other Gmail users’ feedback for future categorizations.

Spam filters are both effective and personalized. Even though spam was 68% of email traffic in 2012, you saw much less in your inbox.

The power of supervised machine learning in fraud detection

In spam filtering, supervised machine learning is common. In fraud detection, it’s not. Using machine learning technology, like Sift Science’s, to detect fraud requires extraordinary technical expertise.

Three reasons why:

  • Higher stakes: You don’t lose emails marked as spam. In contrast, once you turn down a customer, that’s it. With the risks of foregone revenue, lost lifetime value, and a Twitter tantrum, you must balance the costs of fraud with the realities of your business. You need more than a score. Best-in-class, supervised machine learning offers both scores and information.

The question is “Is this customer a fraduster,” so you deserve more than just a number.

  • More diversity: Spam is less diverse than fraud. Fraud patterns vary by factors like your industry, business model, geography, customer base, and inventory. Fortunately, a quality machine learning model can be customized to your business. You can include whatever signals you want (e.g.  “pants size”) and understand how they’re associated with fraud (“A 38 x 32 for a customer in Japan is suspicious based on other orders on your site”).

  • More data: Spam emails are not human beings. Fraudsters are, and their aim is to dupe you. Fortunately, the number of potential fraud signals is huge, and a robust machine learning model can make sense of both unconventional signals (“Page navigation”) and millions of patterns for those signals (“Users visiting sale products in alphabetical order are often fraudulent”).

Stay tuned for more explanations, applications, and discussion on machine learning. If there are specific topics you’d like us to cover, let us know at info@siftscience.com or @siftscience!

Related

featuredmachine learning

Stephanie Yee

Stephanie Yee was a Director at Sift.

  • < prev
  • Blog Home
  • next >
  • Company
  • Get a free demo
  • About us
  • Careers
  • 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

Get industry trends, insights, and actionable fraud-fighting tips.

You're on the list.

You can unsubscribe at any time. Please see our Website Privacy Notice.
Do Not Sell My Personal Information

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

© 2023 Sift Science, Inc. All rights reserved. Sift and the Sift logo are trademarks or registered trademarks of Sift Science, Inc.
Privacy & Terms

Secure your business from login to chargeback

Stop fraud, break down data silos, and lower friction with Sift.

  • Achieve up to 285% ROI
  • Increase user acceptance rates up to 99%
  • Drop time spent on manual review up to 80%
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.