As an e-commerce fraud analyst, you’re expected to decide whether a transaction is good or bad, often with ambiguous transaction and customer data. This can leave you feeling like Lucy, especially during the holiday season.

In the absence of a fraud detection system, here are five signals you can use to assess fraud risk. Remember, these are aggregate signals based on data from many companies. Your mileage may vary.

  1. Fraudsters have stacks on stacks of cards. If the customer has multiple credit cards on file from different banks, their order is 7x more likely fraudulent.
  2. fraudsters dislike capital letters. if a customer wrote their billing name in all lowercase letters, the order is 2.7x more suspicious.
  3. Fraudsters stay (virtually) on the move. A buyer with multiple billing zip codes within a week is 30x more likely to be fraudulent.
  4. Fraudsters favor disposable email addresses. An email address with two or more digits is twice as likely to be fraud than one with zero or one digit.
  5. Fraudsters are night owls. Transactions at 2AM are 50% more likely fraudulent, while 4AM transactions are 100% more likely fraudulent.

How can you further improve your fraud detection accuracy? Customization. Advanced fraud detection solutions like Sift Science can incorporate data unique to your business into our scoring. We call these custom events.

For example, an online shoe store like Zappos could send us the shoe size for each transaction as a custom event. It might turn out that size 10 shoes are more fraudulent than size 15 shoes. This makes sense intuitively: there are more people walking around with size 10 feet and fraudsters often focus on goods they can resell easily. Wondering how Sift Science can solve your e-commerce fraud challenges? Drop us a line, we’d love to help.

Tags: ,

  1. One quick clarification if you don’t mind – I’ve heard the late night fraud indicator before – but is that the users time zone or your own?
    I’d just guess you mean the users time zone, as otherwise it’s just a proxy for international orders which are already more likely to be fraudulent.

  2. Another great way of detecting fraud, but requires work, is to have your system alert you if there is one or more blank spaces entered at the beginning or ending of the credit card field.
    For example ” 1111 2222 3333 4444″ or “1111 2222 3333 4444 ”

    The reason for this is because a lot of fraudsters keep card details stored somewhere either in a file or in a database and will quickly copy/paste information.

    This has the side effect of sometimes adding extra spaces before/after the data. It’s a good indicator when looked at along with other things because why would someone press spacebar 2/3/4 times after entering their card details?

    Want to know another great trick? When fraudsters steal batches of credit card numbers most of the names they get are like “Morgan P Freemon” – Middle names are very really spelt out… just the beginning letter is given.

    If you think the payment may be dodgy, give them a ring and ask for their full name.

    They will normally say “Morgan Freemon”…

    Then ask for their middle name. 99% of the time, this will throw them off as they don’t know the middle name and you can hear them fumble as they think one up.

  3. A question about the lack of capital letters: Is this the sort of thing your system figures out automatically from the text, or is it up to me to submit this as a feature (custom field/event) of the data?

    1. Hi David,We figure out the capitalization from your text automatically. No need to submit a custom field for that (although we do love other custom fields/events given their potential to improve model accuracy).

  4. Hi Steve,
    regarding your bullet point 4 I fully agree: disposable email addresses are often used by fraudsters. Detecting them is hard – new domains for such services appear almost every day.

    That’s why we startet a managed service accessible through an api that helps to detec such domains. See I would love to cooperate.

    Please let me know what you think.

    Kind regards,


  5. Definitely believe that which you stated. Your favorite justification appearedto be on the internet the easiest thing to be aware of.
    I say to you, I definitely get annoyed while people
    think about worries that they plainly don’t know about. You managed
    to hit the nail upon the top as well as defined out the whole thing without having side-effects , people can take a signal.
    Will probably be back to get more. Thanks